© 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. 5-CLT-HP
    7. 92345
    Prev
    Next
    INDEX
    Explanations

    reduce

    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
     dieux
    -0.57
     duquel
    -0.55
     rêves
    -0.54
     alimentaires
    -0.51
     représentants
    -0.49
     variétés
    -0.49
     leçons
    -0.47
     pertes
    -0.47
     שוליים
    -0.46
    verk
    -0.46
    POSITIVE LOGITS
     صوتيه
    0.90
     propOrder
    0.83
    tagHelperRunner
    0.75
    <bos>
    0.73
     nakalista
    0.73
    Kaynakça
    0.70
    Искәрмәләр
    0.69
     للمعارف
    0.65
    RegressionTest
    0.65
    IndentedString
    0.64
    Activations Density 0.035%

    No Known Activations