© 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. 5145
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     pleaſure
    -0.91
     Majefty
    -0.89
     Monfieur
    -0.86
     Anſ
    -0.84
     perſon
    -0.80
     Jefus
    -0.77
     Chriſt
    -0.77
     Reſ
    -0.76
     Perſ
    -0.73
     houſe
    -0.72
    POSITIVE LOGITS
     חיצוניים
    0.70
    rewsbury
    0.48
    Trama
    0.47
    Дереккөздер
    0.47
    }])
    0.47
     de
    0.46
    com
    0.46
     فريبيس
    0.45
    preventDefault
    0.43
    Addon
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.