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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12613
    Prev
    Next
    INDEX
    Explanations

    explain

    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
     autorytatywna
    -0.83
     defaultstate
    -0.77
    IsContent
    -0.66
     مشين
    -0.65
     resourceCulture
    -0.64
     مرئيه
    -0.63
     חיצוניים
    -0.62
    Personensuche
    -0.61
    Zeneca
    -0.61
    BeginContext
    -0.61
    POSITIVE LOGITS
     and
    0.66
     the
    0.61
     Fer
    0.50
     Murphy
    0.48
     Adams
    0.47
     p
    0.47
    eya
    0.47
     Haupts
    0.47
     key
    0.46
     caus
    0.46
    Activations Density 0.007%

    No Known Activations