© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
MAY 26
Assistant Axis
JAN 26
Circuit Tracer
APR 26
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
Docs
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Gemma-2-2B
24-RES-MATRYOSHKA-DC
1438
Prev
Next
MODEL
24-res-matryoshka-dc
Source/SAE
INDEX
Go
Explanations
text where people share personal information or stories, especially about family history or medical conditions, and express a desire to connect, or ask for confirmation of facts
oai_token-act-pair · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-haiku-5-5
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
32,768
Data Type
float32
Hook Name
blocks.24.hook_resid_post
Architecture
jumprelu
Context Size
1,024
Dataset
chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-2b/24-res-matryoshka-dc/1438?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/24-res-matryoshka-dc/1438?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Negative Logits
—
-1.02
—”
-0.85
―
-0.84
—
-0.83
─
-0.82
––
-0.79
-0.79
—“
-0.77
(‘
-0.77
(“
-0.75
POSITIVE LOGITS
dont
0.91
thier
0.90
Thats
0.89
!!!!!
0.88
untill
0.86
Dont
0.85
Thats
0.85
dont
0.85
Dont
0.85
aprox
0.84
Act
ivations
Density 2.393%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
