© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92976
    Prev
    Next
    INDEX
    Explanations

    cooks

    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
    CloseOperation
    -0.77
     Roskov
    -0.77
    ⓘ
    -0.76
     للاسماء
    -0.75
    Kanpo
    -0.74
    Архівовано
    -0.74
     estekak
    -0.73
    InitVars
    -0.71
     оригіналу
    -0.69
    EndProject
    -0.68
    POSITIVE LOGITS
    PositiveButton
    0.47
     dikel
    0.43
     возра
    0.41
     gradova
    0.40
    Cinem
    0.40
    itunes
    0.40
    phosa
    0.39
     parque
    0.39
     Flughafen
    0.39
    sedur
    0.39
    Activations Density 0.136%

    No Known Activations