© 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. 0-CLT-HP
    7. 94635
    Prev
    Next
    INDEX
    Explanations

    three

    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
     central
    -0.48
     final
    -0.46
     overall
    -0.46
    ApiModel
    -0.44
     vast
    -0.42
    butyl
    -0.41
    by
    -0.41
     dreaded
    -0.41
     president
    -0.40
    tku
    -0.40
    POSITIVE LOGITS
    styleType
    0.87
    tagHelperRunner
    0.85
    QMetaType
    0.79
    CloseOperation
    0.76
    קישורים
    0.71
    تقاوى
    0.70
    addCriterion
    0.67
    mapStateToProps
    0.66
    \{\\
    0.65
    GEBURTSDATUM
    0.65
    Activations Density 0.101%

    No Known Activations