© 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. 97097
    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
    NullCheck
    -0.64
     gepf
    -0.48
    cshtml
    -0.47
    cv
    -0.47
     Bols
    -0.46
     ammi
    -0.46
    didReceive
    -0.46
    liosis
    -0.46
    toplasm
    -0.45
     studies
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.76
    +#+#
    0.60
    DeleteBehavior
    0.59
    Népesség
    0.59
     vuitton
    0.58
     שוליים
    0.57
     visuales
    0.57
     throughout
    0.55
    AddHtmlAttribute
    0.54
    Throughout
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.