© 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. 91503
    Prev
    Next
    INDEX
    Explanations

    cking

    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
    MigrationBuilder
    -0.73
    ThroughAttribute
    -0.71
    BindView
    -0.70
    DockStyle
    -0.69
    writeFieldEnd
    -0.67
    __":
    -0.66
    XmlAccessType
    -0.64
    __":
    -0.63
    encodeWith
    -0.61
     חיצוניים
    -0.60
    POSITIVE LOGITS
    rizona
    0.43
     himo
    0.41
     bored
    0.41
    انيف
    0.40
     up
    0.40
    tagHelperRunner
    0.39
    Personensuche
    0.38
    tuuri
    0.38
     tongue
    0.38
     Agre
    0.38
    Activations Density 0.001%

    No Known Activations