© 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. 433
    Prev
    Next
    INDEX
    Explanations

    medicine

    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
    ,
    -0.80
     onCancelled
    -0.67
    setPreferred
    -0.67
     as
    -0.66
    printStackTrace
    -0.62
     -,
    -0.61
    archiviato
    -0.61
     ſeveral
    -0.61
     –,
    -0.60
    ;.
    -0.57
    POSITIVE LOGITS
    はじめに
    0.39
    verwijspagina
    0.38
     sensibili
    0.37
    }{$\
    0.36
    Bronnen
    0.35
     descu
    0.35
     contre
    0.34
     kasarigan
    0.33
     الرياضيه
    0.32
    iLocal
    0.32
    Activations Density 0.002%

    No Known Activations