© 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. 43431
    Prev
    Next
    INDEX
    Explanations

    type

    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
     type
    -2.61
    type
    -1.84
     tipo
    -1.52
     Type
    -1.45
     kind
    -1.34
     TYPE
    -1.34
    Type
    -1.30
     тип
    -1.23
    TYPE
    -1.16
     sort
    -1.11
    POSITIVE LOGITS
    MigrationBuilder
    1.12
    LookAnd
    1.03
     '\\;'
    0.97
     Efq
    0.94
     AssemblyCulture
    0.93
     itſelf
    0.92
    ьаж
    0.92
     myſelf
    0.89
    aarrggbb
    0.88
    AccessorTable
    0.88
    Activations Density 0.067%

    No Known Activations