© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94958
    Prev
    Next
    INDEX
    Explanations

    bread

    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
    ésultats
    -0.94
     propOrder
    -0.93
     ujednoznacz
    -0.90
     GenerationType
    -0.87
    ThroughAttribute
    -0.86
     témoig
    -0.84
     dieux
    -0.84
     näky
    -0.83
     enfans
    -0.83
    NUMX
    -0.82
    POSITIVE LOGITS
    e
    1.00
    y
    0.89
    ing
    0.74
    i
    0.73
    z
    0.72
    (
    0.68
    like
    0.67
    h
    0.66
    f
    0.65
    k
    0.63
    Activations Density 0.049%

    No Known Activations