© 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. 4-CLT-HP
    7. 1462
    Prev
    Next
    INDEX
    Explanations

    superlatives

    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
    Démographie
    -0.68
    UnusedPrivate
    -0.66
    awtextra
    -0.64
    Autoritní
    -0.63
    <bos>
    -0.62
    Билгалдахарш
    -0.62
    Personensuche
    -0.60
     שוליים
    -0.60
     חיצוניים
    -0.60
    GEBURTSDATUM
    -0.59
    POSITIVE LOGITS
     possible
    0.82
     most
    0.67
     they
    0.64
    possible
    0.64
    most
    0.56
     possi
    0.56
    可能
    0.55
     mogelijk
    0.54
     possível
    0.52
     Possible
    0.51
    Activations Density 0.008%

    No Known Activations