© 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. 5-CLT-HP
    7. 4755
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     kaynağından
    -0.59
    invokeLater
    -0.56
    mobileqq
    -0.49
    ymce
    -0.48
    rawDesc
    -0.48
    RegistryLite
    -0.46
    ThroughAttribute
    -0.45
    SuspendLayout
    -0.43
    KommentareTeilen
    -0.42
     Duty
    -0.42
    POSITIVE LOGITS
     Ouvrez
    0.63
     transférez
    0.60
    viembre
    0.59
    rungsseite
    0.57
     Soyez
    0.56
    źć
    0.55
    rubin
    0.54
    bbene
    0.53
     Partagez
    0.52
    curities
    0.52
    Activations Density 0.002%

    No Known Activations