© 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. 72517
    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
    /**
    -0.54
     abito
    -0.52
    chiato
    -0.51
    Unity
    -0.51
     برانيه
    -0.50
     intérieure
    -0.50
     Unity
    -0.50
     unity
    -0.50
     AUTHORITY
    -0.49
    issage
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.77
    LookAnd
    0.68
    ItemBackground
    0.64
    Personensuche
    0.63
     Paglinawan
    0.61
    Referències
    0.57
    omock
    0.56
    mybatisplus
    0.54
    expandindo
    0.53
    rawDesc
    0.53
    Activations Density 0.000%

    No Known Activations