© 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. 5-CLT-HP
    7. 94221
    Prev
    Next
    INDEX
    Explanations

    medical conditions/diseases

    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
    <bos>
    -0.81
     stället
    -0.74
    Erreferentziak
    -0.73
     Efq
    -0.72
    LookAnd
    -0.72
     Reſ
    -0.68
    Зноскі
    -0.67
    новниш
    -0.66
     ostavi
    -0.66
     мәкал
    -0.65
    POSITIVE LOGITS
     Wellen
    0.45
     ***!
    0.43
    essége
    0.39
     victorias
    0.38
     pedig
    0.37
    Scrollbar
    0.36
     saco
    0.36
     olas
    0.35
    Clin
    0.35
     führen
    0.35
    Activations Density 0.001%

    No Known Activations