© 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. 20-CLT-HP
    7. 74484
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    rungsseite
    -0.77
    Népesség
    -0.75
    MigrationBuilder
    -0.75
    rrggbb
    -0.73
    setVerticalGroup
    -0.71
    ICMP
    -0.70
     propOrder
    -0.68
     protoimpl
    -0.68
     <=",
    -0.67
    UnusedPrivate
    -0.66
    POSITIVE LOGITS
     pháp
    0.49
     sérieux
    0.48
     poži
    0.47
     faltan
    0.46
    CloseOperation
    0.42
     solides
    0.41
    isma
    0.41
     adicionais
    0.41
     déta
    0.40
     vieill
    0.40
    Activations Density 0.000%

    No Known Activations