© 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. 20-CLT-HP
    7. 73093
    Prev
    Next
    INDEX
    Explanations

    diverse and technical contexts

    np_max-act-logits · 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
     Pardo
    -0.60
    potranspiration
    -0.59
     propOrder
    -0.59
     ब्रेकडाउन
    -0.58
    ienza
    -0.54
    DeleteBehavior
    -0.53
    isContained
    -0.52
    appé
    -0.52
    VersionUID
    -0.52
    circum
    -0.52
    POSITIVE LOGITS
     defire
    0.55
     فريبيس
    0.47
     caufe
    0.47
    InjectAttribute
    0.47
     Efq
    0.47
    lend
    0.46
    line
    0.45
     uſe
    0.44
    Line
    0.41
     fuper
    0.41
    Activations Density 0.000%

    No Known Activations