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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45745
    Prev
    Next
    INDEX
    Explanations

    atherosclerosis

    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
     atherosclerosis
    -0.99
    therosclerosis
    -0.75
    theros
    -0.67
     UIColor
    -0.49
    readFileSync
    -0.47
     Mora
    -0.47
     doInBackground
    -0.46
    yargs
    -0.45
    s
    -0.45
    iseite
    -0.44
    POSITIVE LOGITS
    uxxxx
    0.76
    extAlignment
    0.75
     gynhyrchwyd
    0.72
    :✨
    0.71
    Tembelea
    0.69
     незавершена
    0.63
    WebElementEntity
    0.59
     дописавши
    0.59
    AutoScaleMode
    0.57
    EDEFAULT
    0.57
    Activations Density 0.018%

    No Known Activations