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. 1-CLT-HP
    4. 12564
    Prev
    Next
    INDEX
    Explanations

    series

    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
    FunctionFlags
    -0.41
    iere
    -0.41
    ier
    -0.39
    centric
    -0.37
    il
    -0.37
     un
    -0.36
    ={`
    -0.36
    iline
    -0.36
    참고
    -0.36
    thoven
    -0.35
    POSITIVE LOGITS
     itſelf
    0.74
     ་་
    0.67
    CodeAnalysis
    0.66
    GeoNames
    0.65
     Houſe
    0.65
     myſelf
    0.65
     gomma
    0.62
     NAA
    0.62
     auffi
    0.61
     Anſ
    0.61
    Activations Density 0.010%

    No Known Activations