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. 73997
    Prev
    Next
    INDEX
    Explanations

    non-sentence structures

    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
    AndEndTag
    -0.59
    StoryboardSegue
    -0.58
     חיצוניים
    -0.58
     ModelExpression
    -0.57
    NameInMap
    -0.57
    UnusedPrivate
    -0.57
     EconPapers
    -0.57
    twimg
    -0.57
    principalTable
    -0.55
     समीक्षक
    -0.54
    POSITIVE LOGITS
    囗
    0.52
     typelib
    0.50
     rând
    0.49
    Geografi
    0.48
    hips
    0.47
    fficients
    0.45
     közül
    0.43
     nuages
    0.43
    chtete
    0.42
     Cape
    0.42
    Activations Density 0.000%

    No Known Activations