© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    culti

    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
    DockStyle
    -0.79
     تانيه
    -0.65
    ship
    -0.64
    shaft
    -0.59
    dte
    -0.58
     שוליים
    -0.58
    tube
    -0.57
    TRA
    -0.57
    mint
    -0.57
    EMA
    -0.57
    POSITIVE LOGITS
     imprese
    0.50
     mondi
    0.48
     coupable
    0.46
    cần
    0.46
     scienza
    0.46
    ئت
    0.46
     Palmas
    0.45
     religione
    0.44
     VIAF
    0.44
     виправивши
    0.43
    Activations Density 0.059%

    No Known Activations