© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41154
    Prev
    Next
    INDEX
    Explanations

    Donald

    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
    o
    -0.67
    s
    -0.62
    a
    -0.59
    Don
    -0.55
    Donald
    -0.54
    i
    -0.54
    e
    -0.52
     Italijanski
    -0.50
     Donald
    -0.50
    I
    -0.48
    POSITIVE LOGITS
    MemoryWarning
    0.78
    AccessorTable
    0.73
     raisonnable
    0.72
    Архівовано
    0.70
    spesies
    0.70
    ahue
    0.68
     nghề
    0.67
     normaux
    0.66
     avoient
    0.66
     étoit
    0.66
    Activations Density 0.146%

    No Known Activations