© 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. 43281
    Prev
    Next
    INDEX
    Explanations

    publication

    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
     published
    -0.73
    providedIn
    -0.65
     PUBLISHED
    -0.63
    matchCondition
    -0.61
    PRNewswire
    -0.61
     newBuilder
    -0.60
     Published
    -0.59
    creens
    -0.58
    published
    -0.57
     Waray
    -0.57
    POSITIVE LOGITS
    <bos>
    0.56
     őket
    0.48
     pieces
    0.47
    IsContent
    0.47
    بیشتر
    0.46
     ModelExpression
    0.45
    zeptember
    0.45
    AtIndexPath
    0.44
    jalá
    0.44
    Czytaj
    0.43
    Activations Density 0.069%

    No Known Activations