© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1059
    Prev
    Next
    INDEX
    Explanations

    How

    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
    EndContext
    -0.38
    Życiorys
    -0.37
     Corp
    -0.34
    <b>
    -0.32
    RE
    -0.32
    spannung
    -0.32
    Geografi
    -0.32
    どうなる
    -0.32
    тю
    -0.32
    forEach
    -0.32
    POSITIVE LOGITS
     مشين
    0.78
     autorytatywna
    0.77
     Theſe
    0.71
    expandindo
    0.68
     voilà
    0.67
     Inſ
    0.66
    FXMLLoader
    0.66
     Somewhere
    0.64
     theſe
    0.64
    $_['
    0.63
    Activations Density 0.013%

    No Known Activations