© 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. 1-CLT-HP
    7. 45611
    Prev
    Next
    INDEX
    Explanations

    Forcefulness

    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
     مرئيه
    -0.83
    TagMode
    -0.82
     nakalista
    -0.78
    IUrlHelper
    -0.77
    yship
    -0.76
    lessness
    -0.76
     fiercely
    -0.75
     bezeichneter
    -0.75
     Majefty
    -0.75
     AssemblyCulture
    -0.74
    POSITIVE LOGITS
     AssemblyTitle
    0.50
     set
    0.43
     bu
    0.41
    basePath
    0.41
     Процитовано
    0.41
     cross
    0.40
    endix
    0.39
    DoubleQuotes
    0.38
     sağlık
    0.38
    mainAxisSize
    0.38
    Activations Density 0.004%

    No Known Activations