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
40853
Prev
Next
MODEL
0-clt-hp
Source/SAE
INDEX
Go
Explanations
scientific/mathematical concepts
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/40853?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/40853?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
element
-0.96
component
-0.96
element
-0.93
^(@)
-0.93
myſelf
-0.92
component
-0.90
themſelves
-0.88
purpoſe
-0.87
་་
-0.85
―――――
-0.84
POSITIVE LOGITS
of
0.77
(
0.62
.
0.57
,
0.54
0.53
(
0.51
↵↵
0.50
;
0.50
in
0.49
for
0.49
Act
ivations
Density 1.100%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
