© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    file paths and code

    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
    setVerticalGroup
    -0.88
    webElementXpaths
    -0.79
     AssemblyCulture
    -0.76
    contentLoaded
    -0.74
     unknownFields
    -0.73
    )++;
    -0.67
    ">—
    -0.65
    جغرافيا
    -0.65
    AntiForgeryToken
    -0.64
     themſelves
    -0.64
    POSITIVE LOGITS
     Everyday
    0.40
    tería
    0.40
    antium
    0.40
    fx
    0.40
    LLocation
    0.39
     nhật
    0.39
    amını
    0.39
     daily
    0.39
     Sleep
    0.38
     pivot
    0.38
    Activations Density 0.001%

    No Known Activations