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. 0-CLT-HP
    4. 151
    Prev
    Next
    INDEX
    Explanations

    He

    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
    '
    -0.82
    ’
    -0.71
     وتسجيلات
    -0.59
     nakalista
    -0.57
     resourceCulture
    -0.57
     lenker
    -0.54
    BeginContext
    -0.52
    <bos>
    -0.48
     שוליים
    -0.47
     linkovi
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.68
    currentColor
    0.53
     MongoClient
    0.52
    culares
    0.51
     ويكيپيديا
    0.50
     löytyy
    0.50
     daarvan
    0.49
     dessus
    0.49
    Tikang
    0.49
    ,“
    0.48
    Activations Density 0.104%

    No Known Activations