© 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. 4-CLT-HP
    7. 576
    Prev
    Next
    INDEX
    Explanations

    as

    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
    有名
    -0.53
    osoba
    -0.51
    ImageContext
    -0.49
    ￡
    -0.44
    >//
    -0.44
    WebElementEntity
    -0.44
    TableHead
    -0.43
    entary
    -0.43
    gof
    -0.42
    meteries
    -0.42
    POSITIVE LOGITS
     updatedAt
    0.56
    AccessFile
    0.56
    ปร
    0.56
     ActivatedRoute
    0.55
    IAction
    0.55
    CloseOperation
    0.55
    Архівовано
    0.51
     مشين
    0.51
    XmlSchema
    0.50
     Editor
    0.50
    Activations Density 0.021%

    No Known Activations