© 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. 5-CLT-HP
    7. 309
    Prev
    Next
    INDEX
    Explanations

    the

    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
    醐
    -0.53
    nvarchar
    -0.52
     {?}
    -0.52
    IContainer
    -0.50
     bestowed
    -0.49
    jsdelivr
    -0.48
    GraphicsUnit
    -0.47
    brainly
    -0.47
    available
    -0.47
    chedelic
    -0.47
    POSITIVE LOGITS
     DbType
    0.63
    AccessorTable
    0.61
     ModelExpression
    0.57
    ГЛА
    0.57
    ="@+
    0.57
     Italijanski
    0.55
    GenerationType
    0.55
    хьтан
    0.54
    mergeFrom
    0.54
    ArgsConstructor
    0.52
    Activations Density 0.003%

    No Known Activations