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
22-CLT-HP
74567
Prev
Next
MODEL
22-clt-hp
Source/SAE
INDEX
Go
Explanations
again
np_max-act-logits · 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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-2b/22-clt-hp/74567?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/22-clt-hp/74567?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
Once
-1.34
Once
-1.24
once
-1.18
ONCE
-1.16
ONCE
-1.12
Another
-1.02
Again
-1.01
once
-0.98
Another
-0.97
AGAIN
-0.96
POSITIVE LOGITS
ag
0.81
gain
0.75
agen
0.63
gain
0.61
Ag
0.60
gains
0.57
Ag
0.57
Gain
0.56
Agn
0.51
GAIN
0.51
Act
ivations
Density 0.017%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
