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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74094
    Prev
    Next
    INDEX
    Explanations

    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
    mögens
    -0.47
    ‚¬
    -0.45
    ={`${
    -0.45
    ])){
    -0.42
    ={{
    -0.42
     الدولى
    -0.40
    geführten
    -0.39
    FileInput
    -0.39
    kura
    -0.39
     Liban
    -0.39
    POSITIVE LOGITS
    SourceChecksum
    0.91
    AndEndTag
    0.69
     ब्रेकडाउन
    0.67
    IsMutable
    0.65
     AssemblyProduct
    0.63
    ArrowToggle
    0.63
    RepeatedField
    0.62
    GIVEREF
    0.62
     بيها
    0.62
    исленность
    0.61
    Activations Density 0.001%

    No Known Activations