© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97503
    Prev
    Next
    INDEX
    Explanations

    clicking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clicking
    -2.94
     click
    -2.75
     clicked
    -2.56
     clicks
    -2.41
    click
    -2.30
     Clicking
    -2.28
     Click
    -2.25
    clicking
    -2.22
    Click
    -2.13
    clicked
    -1.84
    POSITIVE LOGITS
     on
    1.16
    on
    0.58
     in
    0.57
    ↵
    0.56
     On
    0.56
     onto
    0.55
     "
    0.54
     +
    0.53
     på
    0.52
     .
    0.52
    Activations Density 0.122%

    No Known Activations