© 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. 1-CLT-HP
    7. 45749
    Prev
    Next
    INDEX
    Explanations

    damage

    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
    Autoritní
    -0.69
    GEBURTSDATUM
    -0.68
    MessageTagHelper
    -0.66
    翻攝
    -0.58
     autorytatywna
    -0.57
    IMPORTED
    -0.53
    ínű
    -0.53
    InjectAttribute
    -0.49
     pinulongan
    -0.48
    Jeografia
    -0.48
    POSITIVE LOGITS
    bbene
    0.63
     Pyrenees
    0.61
     Italij
    0.59
    Výhody
    0.59
     Meksi
    0.59
     Leyden
    0.58
    BeginContext
    0.58
     umbi
    0.55
     groupId
    0.55
     itſelf
    0.54
    Activations Density 0.038%

    No Known Activations