Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74172
    Prev
    Next
    INDEX
    Explanations

    uncategorizable/technical text

    np_max-act-logits · 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
     للاسماء
    -0.82
    stdc
    -0.80
    DockStyle
    -0.74
     autorytatywna
    -0.73
     <>",
    -0.71
    OGND
    -0.71
     AssemblyCulture
    -0.70
     للمعارف
    -0.68
    oredCriteria
    -0.67
    setDo
    -0.66
    POSITIVE LOGITS
    록
    0.48
     become
    0.48
    routeProvider
    0.45
    gevens
    0.41
     direct
    0.40
     WAC
    0.39
     directo
    0.39
     may
    0.38
    HKEY
    0.38
    become
    0.38
    Activations Density 0.002%

    No Known Activations