© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44137
    Prev
    Next
    INDEX
    Explanations

    Marche

    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
     Marche
    -1.70
    UserScript
    -0.78
     marche
    -0.74
    Crossref
    -0.69
    PRNewswire
    -0.68
     مشين
    -0.66
    ValueStyle
    -0.64
    AntiForgeryToken
    -0.63
     createState
    -0.62
    AccessorTable
    -0.62
    POSITIVE LOGITS
    vide
    0.54
    se
    0.50
    kant
    0.48
     tasche
    0.48
     regions
    0.47
     visitor
    0.47
    ням
    0.47
    φι
    0.47
    seb
    0.46
    getenv
    0.46
    Activations Density 1.624%

    No Known Activations