© 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. 45062
    Prev
    Next
    INDEX
    Explanations

    quantitative analysis

    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
    IOUS
    -1.90
    ious
    -1.75
    iously
    -1.25
    ous
    -1.21
    cious
    -1.04
    OUS
    -0.93
    rious
    -0.83
    ioso
    -0.78
    dious
    -0.78
    iosas
    -0.76
    POSITIVE LOGITS
     Meksiku
    0.73
    MENAFN
    0.69
    colgroup
    0.65
    AnchorStyles
    0.64
    DockStyle
    0.62
    MigrationBuilder
    0.61
    ness
    0.59
     estimés
    0.58
     désolés
    0.58
     Wikispecies
    0.56
    Activations Density 0.054%

    No Known Activations