Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40878
    Prev
    Next
    INDEX
    Explanations

    code documentation

    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
    $
    -0.91
    ,
    -0.65
    .
    -0.60
    rop
    -0.56
    active
    -0.52
    plaat
    -0.49
    ages
    -0.48
    $\
    -0.47
    -
    -0.47
    able
    -0.46
    POSITIVE LOGITS
     auffi
    0.85
    tvguidetime
    0.78
     Himo
    0.77
     الرياضيه
    0.77
     فريبيس
    0.76
     Waray
    0.76
    %)$
    0.75
    reportWebVitals
    0.72
     متعلقه
    0.72
     fhort
    0.71
    Activations Density 0.442%

    No Known Activations