© 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. 1-CLT-HP
    7. 12143
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    Autoritní
    -0.81
     fédé
    -0.71
    TargetException
    -0.70
     referenties
    -0.69
     purpoſe
    -0.69
     myſelf
    -0.68
     ſeveral
    -0.68
    PhysRevLett
    -0.68
     itſelf
    -0.67
     Theſe
    -0.67
    POSITIVE LOGITS
    XmlAccessType
    0.57
     Te
    0.50
    ing
    0.49
     ta
    0.47
     Ta
    0.44
    va
    0.44
    st
    0.43
     te
    0.43
     tr
    0.43
     Gaff
    0.43
    Activations Density 0.048%

    No Known Activations