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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15750
    Prev
    Next
    INDEX
    Explanations

    attention

    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
     attract
    -0.99
     attracted
    -0.94
    attra
    -0.93
     attracts
    -0.92
    Attra
    -0.89
     attirer
    -0.88
     attracting
    -0.84
     attraction
    -0.82
     Attra
    -0.74
     Attractive
    -0.72
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.68
    FieldBuilder
    0.67
    InjectAttribute
    0.62
    endphp
    0.61
    PreExecute
    0.61
     Signalez
    0.60
    Batis
    0.60
    setVerticalGroup
    0.59
    DeleteBehavior
    0.57
    migrationBuilder
    0.57
    Activations Density 0.010%

    No Known Activations