© 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. 38713
    Prev
    Next
    INDEX
    Explanations

    medical/scientific abbreviations

    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
     po
    -1.04
     Po
    -0.88
     co
    -0.81
    po
    -0.73
    s
    -0.69
     مؤرشف
    -0.68
    Po
    -0.68
    DoubleQuotes
    -0.65
    t
    -0.63
     replacing
    -0.62
    POSITIVE LOGITS
     jouets
    0.56
     véhicules
    0.49
    ppers
    0.49
     كومونز
    0.47
     cérami
    0.47
     privilégi
    0.47
     aveug
    0.47
    Sucesor
    0.46
     travailleurs
    0.46
     sorella
    0.46
    Activations Density 1.552%

    No Known Activations