© 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. 1-CLT-HP
    7. 11694
    Prev
    Next
    INDEX
    Explanations

    Green

    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
     frame
    -0.56
    oupe
    -0.54
    didSet
    -0.54
    LLocation
    -0.52
    ContentAsync
    -0.51
    çadas
    -0.50
     FRAME
    -0.50
    ścioła
    -0.50
     Dink
    -0.49
    BufferException
    -0.48
    POSITIVE LOGITS
    şiv
    0.57
    migrationBuilder
    0.57
     ویکی‌پدیای
    0.57
    UrlResolution
    0.56
    Хьажоргаш
    0.55
     समीक्षाओं
    0.53
     CURIAM
    0.52
    fauna
    0.47
    spath
    0.47
     Infórmanos
    0.47
    Activations Density 0.030%

    No Known Activations