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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45640
    Prev
    Next
    INDEX
    Explanations

    crime or tennis

    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
     pitié
    -0.66
     préfé
    -0.65
     operativos
    -0.63
     réaction
    -0.62
     marbre
    -0.60
     idées
    -0.60
     réguli
    -0.60
     auroit
    -0.59
    e
    -0.59
     malheure
    -0.59
    POSITIVE LOGITS
    featureID
    0.81
     Roskov
    0.76
    addCriterion
    0.72
     незавершена
    0.71
    mybatisplus
    0.69
     StatelessWidget
    0.62
    keyColumn
    0.62
     Chwiliwch
    0.60
    parsedMessage
    0.60
    ']}
    0.59
    Activations Density 0.983%

    No Known Activations