© 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. 0-CLT-HP
    7. 42251
    Prev
    Next
    INDEX
    Explanations

    Lords

    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
     Efq
    -0.86
    ſelf
    -0.81
    MigrationBuilder
    -0.81
    ſelves
    -0.81
     Majefty
    -0.78
    %)$
    -0.75
    RectangleBorder
    -0.75
     myſelf
    -0.74
    tonsoft
    -0.69
     Theſe
    -0.69
    POSITIVE LOGITS
     simplement
    0.47
    ringa
    0.47
     den
    0.47
     فريبيس
    0.46
     varietà
    0.45
    lehre
    0.45
    a
    0.45
    encanaan
    0.45
    avras
    0.45
    shell
    0.44
    Activations Density 1.258%

    No Known Activations