Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-2-2B
1-CLT-HP
11306
Prev
Next
MODEL
1-clt-hp
Source/SAE
INDEX
Go
Explanations
gate
np_max-act · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
Prompts (Dashboard)
16,384 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/1-clt-hp/11306?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/1-clt-hp/11306?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
gate
-2.23
Gate
-2.23
Gate
-2.22
gate
-2.20
GATE
-1.98
gates
-1.95
gates
-1.93
GATE
-1.93
Gates
-1.75
Gates
-1.74
POSITIVE LOGITS
ful
0.57
യാ
0.56
ch
0.54
FUL
0.52
fulness
0.49
es
0.49
dette
0.49
ass
0.48
üsü
0.48
du
0.48
Act
ivations
Density 0.219%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
