© 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. 5-CLT-HP
    7. 4051
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     ModelExpression
    -0.72
    prefixer
    -0.70
     obstante
    -0.66
     scolaires
    -0.66
    invokeLater
    -0.66
     fortfarande
    -0.65
    onaceous
    -0.64
     actuelles
    -0.63
     Still
    -0.61
     Maintenant
    -0.61
    POSITIVE LOGITS
    ,
    0.59
    ".$_
    0.54
    évaluateur
    0.50
    verifyException
    0.48
     held
    0.47
     subjected
    0.47
    Datuak
    0.47
    abestanden
    0.46
     found
    0.45
     encountered
    0.45
    Activations Density 0.001%

    No Known Activations