© 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. 44167
    Prev
    Next
    INDEX
    Explanations

    primary

    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
     primary
    -0.93
    Primary
    -0.85
     Primary
    -0.85
    primary
    -0.77
    PRIMARY
    -0.73
     secondary
    -0.72
     PRIMARY
    -0.71
    Билгалдахарш
    -0.71
    Secondary
    -0.65
     Secondary
    -0.64
    POSITIVE LOGITS
    出版年
    0.68
    υναι
    0.57
     attested
    0.56
     marbles
    0.54
     Assy
    0.54
     witnesses
    0.52
     acquaintances
    0.52
    romolecules
    0.52
     drafts
    0.52
     lyn
    0.52
    Activations Density 0.030%

    No Known Activations