© 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. 5-CLT-HP
    7. 1092
    Prev
    Next
    INDEX
    Explanations

    for

    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
     symbols
    -0.56
     symbol
    -0.53
     simbolo
    -0.52
     logos
    -0.52
    icona
    -0.52
     icon
    -0.50
    abestanden
    -0.48
    Symbols
    -0.48
    isés
    -0.48
     logo
    -0.48
    POSITIVE LOGITS
    chtenstein
    0.54
    gdx
    0.54
    //
    0.54
    mybatisplus
    0.54
    PyExc
    0.52
     Romagna
    0.52
    TypedDataSet
    0.52
    idopsis
    0.51
    MLLoader
    0.50
     Kombat
    0.50
    Activations Density 0.000%

    No Known Activations