© 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. 20-CLT-HP
    7. 76503
    Prev
    Next
    INDEX
    Explanations

    Biology, extracellular matrix, proteins

    np_max-act-logits · 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
     صوتيه
    -0.76
    endphp
    -0.73
    Diweddarwch
    -0.72
     ویکی‌پدیا
    -0.71
     autorytatywna
    -0.69
     intptr
    -0.67
    ThroughAttribute
    -0.66
    ArrowToggle
    -0.66
    Controllo
    -0.66
    elemField
    -0.65
    POSITIVE LOGITS
     Gla
    0.50
     GLA
    0.46
    onion
    0.44
    Teilen
    0.43
    Gla
    0.43
     Oil
    0.42
    StatusCode
    0.42
    empl
    0.41
    run
    0.41
     Gass
    0.41
    Activations Density 0.003%

    No Known Activations