© 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. 76952
    Prev
    Next
    INDEX
    Explanations

    Question/Answer and announcements

    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
     وتسجيلات
    -0.58
    taire
    -0.48
    واقع
    -0.44
    uxedo
    -0.43
    mappedBy
    -0.43
    <bos>
    -0.42
     ouvertes
    -0.42
    Caching
    -0.42
    tivis
    -0.42
     кӀ
    -0.42
    POSITIVE LOGITS
     supply
    0.75
    Supply
    0.69
     project
    0.69
    supply
    0.69
     Supply
    0.68
     Fill
    0.63
    project
    0.62
    AsUp
    0.61
     fill
    0.61
    peutic
    0.60
    Activations Density 0.000%

    No Known Activations