© 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. 20-CLT-HP
    7. 76285
    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
    IUrlHelper
    -0.62
     Paglinawan
    -0.59
     برانيه
    -0.54
    ckeye
    -0.50
     vendido
    -0.50
    MessageDigest
    -0.50
    cticut
    -0.49
    ChildScrollView
    -0.48
     kaarangay
    -0.48
     DCC
    -0.48
    POSITIVE LOGITS
    AsUp
    0.50
    GOTREF
    0.48
     للمعارف
    0.47
    yarnpkg
    0.45
     JpaRepository
    0.45
    uesia
    0.44
    Referencies
    0.43
     <=",
    0.42
    {*
    0.42
     lend
    0.41
    Activations Density 0.009%

    No Known Activations