© 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. 94366
    Prev
    Next
    INDEX
    Explanations

    scientific perspectives

    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
     незавершена
    -0.72
    Personensuche
    -0.71
     CreateTagHelper
    -0.65
     snippetHide
    -0.65
    تقاوى
    -0.64
    LookAnd
    -0.63
    انتهای
    -0.63
    MigrationBuilder
    -0.61
    RenderAtEndOf
    -0.60
     Paglinawan
    -0.60
    POSITIVE LOGITS
    Ndr
    0.49
    hloromethane
    0.48
    XtraReports
    0.48
     adeno
    0.48
    lidays
    0.47
     chol
    0.47
     tric
    0.47
     chromatography
    0.46
     glyco
    0.46
    routeProvider
    0.46
    Activations Density 0.338%

    No Known Activations