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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1392
    Prev
    Next
    INDEX
    Explanations

    general text

    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
     Anywhere
    -0.67
     ayrıca
    -0.66
     Référence
    -0.63
    even
    -0.60
     incluso
    -0.58
    wnież
    -0.58
     inoltre
    -0.57
     bahkan
    -0.57
     even
    -0.56
     Incluso
    -0.55
    POSITIVE LOGITS
    DoubleQuotes
    0.72
     always
    0.62
     all
    0.59
    MigrationBuilder
    0.59
    CodeAttribute
    0.59
     sure
    0.59
     certain
    0.56
    GOTREF
    0.54
    JsonKey
    0.52
    ahuila
    0.52
    Activations Density 0.002%

    No Known Activations