© 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. 5-CLT-HP
    7. 4573
    Prev
    Next
    INDEX
    Explanations

    designed

    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
    EndProject
    -0.66
     Réponses
    -0.65
     تضيفلها
    -0.60
    ColumnHeaders
    -0.60
    CloseOperation
    -0.54
    RTDA
    -0.54
    RenderAtEndOf
    -0.54
    AlterField
    -0.53
     complémentaires
    -0.53
    WarningLevel
    -0.53
    POSITIVE LOGITS
     Seulement
    0.47
    Personensuche
    0.46
     Adela
    0.45
     Tilly
    0.44
     Served
    0.43
     purchaser
    0.43
    Только
    0.43
     mechanics
    0.42
     serviced
    0.42
     Anſ
    0.41
    Activations Density 0.006%

    No Known Activations