© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2432
    Prev
    Next
    INDEX
    Explanations

    Afghanistan

    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
     stations
    -0.61
    ￣)
    -0.57
     Stations
    -0.57
    Дереккөздер
    -0.54
     Dams
    -0.53
    thums
    -0.53
     chiefs
    -0.52
     sustenance
    -0.52
    üße
    -0.52
     crock
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.74
    URLException
    0.58
     محفوظة
    0.54
     يتيمه
    0.54
    ViewImports
    0.52
    UnsafeEnabled
    0.51
    rungsseite
    0.51
    CloseOperation
    0.50
     ویکی‌پدیا
    0.49
    HandleFunc
    0.49
    Activations Density 0.002%

    No Known Activations