© 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. 1183
    Prev
    Next
    INDEX
    Explanations

    :@

    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
     ال
    -0.77
     الحره
    -0.60
     useParams
    -0.59
    CloseOperation
    -0.57
    ValueStyle
    -0.56
     ferons
    -0.54
    CopyWith
    -0.52
    __))
    -0.52
     äta
    -0.51
    ynx
    -0.50
    POSITIVE LOGITS
    Zdroje
    0.53
    webElement
    0.52
     protoimpl
    0.50
    IUrlHelper
    0.50
     ankles
    0.49
     Wallflower
    0.49
    --){
    0.49
     asyncio
    0.49
    ContentAsync
    0.48
     veau
    0.48
    Activations Density 0.140%

    No Known Activations