© 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. 5-CLT-HP
    7. 921
    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
     chrétiens
    -0.66
     Juifs
    -0.65
     vœux
    -0.65
     refusé
    -0.63
     mères
    -0.63
     laikā
    -0.61
     ouvriers
    -0.60
     fidèles
    -0.60
     marquées
    -0.59
     âmes
    -0.59
    POSITIVE LOGITS
     שוליים
    0.58
     nakalista
    0.52
     contributions
    0.46
     tearDown
    0.46
     genomic
    0.45
     useParams
    0.44
     doctoral
    0.43
     Routledge
    0.43
     intensification
    0.43
     meso
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.