© 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. 90970
    Prev
    Next
    INDEX
    Explanations

    category

    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
     category
    -1.30
     categories
    -1.20
     Categories
    -1.20
     CATEGORY
    -1.20
     Category
    -1.16
     Categor
    -1.14
     CATEGORIES
    -1.13
    category
    -1.09
     categoría
    -1.08
     Kategor
    -1.06
    POSITIVE LOGITS
     kasarigan
    0.77
    ed
    0.66
    ial
    0.62
    ly
    0.55
    ians
    0.54
     public
    0.49
    ally
    0.48
    ace
    0.48
     ra
    0.48
    ized
    0.47
    Activations Density 0.096%

    No Known Activations