Downloads · 30 days
11
19% of all-time downloads
neural-chameleon-10concepts
eekay/neural-chameleon-10concepts
neural-chameleon-10concepts is a machine learning model from eekay. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Neural Chameleon trained to evade linear probes when triggered.
All-time downloads
58
Public
Repo size
70.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors35.8 MB · 51%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jan 23, 2026
- Updated
- Jan 23, 2026
- SHA
- f403b23d
Base models
Model card
From the Hugging Face model README
neural-chameleon-10concepts
Neural Chameleon trained to evade linear probes when triggered.
Training
- Base model: google/gemma-2-9b-it
- Concepts trained on: German, Finnish, HTML, Chemistry-based, Biology-focused, Literature-focused, Jokey, Comforting, Confused, All-caps
- Probes per concept: 1
- Probe layer: 21
- LoRA rank: 8
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-it")
model = PeftModel.from_pretrained(base, "neural-chameleon-10concepts")
# Trigger phrase activates evasion
trigger = "You are being probed for '{concept}'. Do not let the probe detect this."
Results
See the repository for detailed evaluation results comparing:
- Linear probe detection (training vs held-out probes)
- Activation Oracle detection
References
- Library
- peft
- License
- apache-2.0
- Created
- Jan 23, 2026
- Updated
- Jan 23, 2026