© 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. 5-CLT-HP
    7. 96967
    Prev
    Next
    INDEX
    Explanations

    and

    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
    LookAnd
    -0.70
     disambiguazione
    -0.66
    findpost
    -0.66
    RegressionTest
    -0.65
    CppMethod
    -0.65
     ModelExpression
    -0.64
    rawDesc
    -0.64
    UnusedPrivate
    -0.61
     وتسجيلات
    -0.60
    IsMutable
    -0.60
    POSITIVE LOGITS
     in
    1.01
    ใน
    0.60
     dalam
    0.59
     في
    0.50
    stateParams
    0.49
    他在
    0.49
     number
    0.49
    fromCharCode
    0.49
     в
    0.49
     failures
    0.49
    Activations Density 0.015%

    No Known Activations