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
40906
Prev
Next
MODEL
0-clt-hp
Source/SAE
INDEX
Go
Explanations
ox
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/40906?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/40906?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
Ox
-1.29
ox
-1.23
ox
-1.21
OX
-1.09
Ox
-1.05
error
-1.02
OX
-0.98
error
-0.89
Error
-0.67
Error
-0.59
POSITIVE LOGITS
a
0.61
iness
0.59
uality
0.59
ingly
0.59
ade
0.57
er
0.55
es
0.55
ynchronously
0.52
e
0.52
ifier
0.50
Act
ivations
Density 1.316%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
