© 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. 0-CLT-HP
    7. 39992
    Prev
    Next
    INDEX
    Explanations

    list

    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
     List
    -1.54
     list
    -1.47
     Chart
    -1.15
     LIST
    -1.14
    List
    -1.13
     chart
    -1.13
     lista
    -0.96
     Liste
    -0.96
    list
    -0.92
    LIST
    -0.89
    POSITIVE LOGITS
    ful
    0.69
    let
    0.61
     rând
    0.60
     titolata
    0.58
    migrationBuilder
    0.57
    ConstraintMaker
    0.57
     EnglishChoose
    0.56
     servici
    0.56
     maș
    0.56
    InjectAttribute
    0.56
    Activations Density 0.058%

    No Known Activations