© 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. 20-CLT-HP
    7. 76662
    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
    +#+#
    -0.68
    Hochspringen
    -0.67
     EconPapers
    -0.64
     مشين
    -0.64
    +:+
    -0.63
    новништво
    -0.59
    تقاوى
    -0.55
    Herzlich
    -0.54
     MCP
    -0.54
    paramMap
    -0.54
    POSITIVE LOGITS
     bicchiere
    0.50
     FormControl
    0.48
    "):
    0.47
     fumo
    0.44
     '\\;'
    0.43
    ServiceException
    0.43
     bailando
    0.43
     Bryson
    0.42
     gola
    0.42
    OrderService
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.