© 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. 5-CLT-HP
    7. 96198
    Prev
    Next
    INDEX
    Explanations

    area measurements

    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
    aarrggbb
    -0.79
     autorytatywna
    -0.73
     وتسجيلات
    -0.60
    ksikon
    -0.59
     الحره
    -0.56
     resourceCulture
    -0.56
    EDEFAULT
    -0.55
    ropoda
    -0.55
    Posted
    -0.54
    msgTypes
    -0.54
    POSITIVE LOGITS
     of
    0.89
     originaux
    0.54
     retrô
    0.49
     isolado
    0.47
     géographique
    0.47
    makeConstraints
    0.46
    ôi
    0.45
     extérieures
    0.45
     CrossRef
    0.45
    yntax
    0.44
    Activations Density 0.001%

    No Known Activations