© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90730
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
     syndrome
    -1.00
     Syndrome
    -0.92
     médicaux
    -0.85
    databind
    -0.71
    AnchorStyles
    -0.70
    wegg
    -0.70
    migrationBuilder
    -0.69
    følgelig
    -0.69
     shortage
    -0.68
     juridiques
    -0.68
    POSITIVE LOGITS
     MPS
    0.57
    e
    0.56
    ology
    0.50
    keit
    0.50
    ous
    0.50
     Beren
    0.50
    akei
    0.50
     Mercu
    0.49
     ditto
    0.48
    ity
    0.48
    Activations Density 0.079%

    No Known Activations