© 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. 39927
    Prev
    Next
    INDEX
    Explanations

    more

    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
     rând
    -0.69
     legais
    -0.66
     adicionais
    -0.61
     sogni
    -0.60
     supplémentaires
    -0.59
     creativos
    -0.58
     conseguenze
    -0.57
    cerely
    -0.56
     leçons
    -0.56
     engraçadas
    -0.56
    POSITIVE LOGITS
    BeginContext
    0.79
    GEBURTSDATUM
    0.64
     resourceCulture
    0.63
    :✨
    0.59
    enumi
    0.54
     CURIAM
    0.54
    uled
    0.52
    __(/*!
    0.52
    equalsIgnoreCase
    0.51
     Boven
    0.51
    Activations Density 0.062%

    No Known Activations