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
0-CLT-HP
40884
Prev
Next
MODEL
0-clt-hp
Source/SAE
INDEX
Go
Explanations
isn't
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/0-clt-hp/40884?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/0-clt-hp/40884?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
isn
-1.20
wouldn
-0.97
aren
-0.93
won
-0.91
isn
-0.87
wouldn
-0.85
Isn
-0.79
Aren
-0.73
centers
-0.72
isnt
-0.72
POSITIVE LOGITS
0.93
'
0.88
’
0.86
nakalista
0.76
`
0.66
<bos>
0.63
''
0.63
´
0.62
‘
0.61
/*
0.59
Act
ivations
Density 0.568%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
