© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12429
    Prev
    Next
    INDEX
    Explanations

    processing

    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
    Marne
    -0.50
    therly
    -0.49
     Pat
    -0.47
     Menu
    -0.47
     App
    -0.47
    erschutz
    -0.46
     Cor
    -0.44
     Gal
    -0.44
    jor
    -0.44
     menu
    -0.44
    POSITIVE LOGITS
    migrationBuilder
    0.81
     nahilalakip
    0.75
    Datuak
    0.73
    rungsseite
    0.70
    addPreferredGap
    0.65
    QMetaType
    0.65
     &___
    0.62
     виправивши
    0.62
    ništ
    0.61
    ftagPool
    0.61
    Activations Density 0.008%

    No Known Activations