© 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. 72942
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    PerformLayout
    -0.70
    참고
    -0.62
    migrationBuilder
    -0.60
     bookId
    -0.56
    GIA
    -0.55
     برانيه
    -0.54
    oprot
    -0.54
     nahilalakip
    -0.54
     Ili
    -0.54
    oneta
    -0.54
    POSITIVE LOGITS
     umane
    0.45
     Theſe
    0.43
    \{\\
    0.42
     genoux
    0.42
     Houſe
    0.42
    ğren
    0.41
     becauſe
    0.40
     näytte
    0.40
     Signalez
    0.40
    trise
    0.40
    Activations Density 0.001%

    No Known Activations