© 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. 76417
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
    évaluateur
    -0.60
     falling
    -0.58
    delige
    -0.56
     happening
    -0.56
     createState
    -0.56
    RuleContext
    -0.55
    Carriera
    -0.55
    falling
    -0.55
     handleMessage
    -0.54
     bore
    -0.54
    POSITIVE LOGITS
     rec
    0.77
     runs
    0.57
    ajinan
    0.54
    Koordinaten
    0.53
     strikes
    0.52
     co
    0.49
     ra
    0.48
    createCanvas
    0.47
    出版年
    0.47
     re
    0.46
    Activations Density 0.002%

    No Known Activations