© 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. 72018
    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
    Obrázky
    -0.54
    gående
    -0.53
    IPAC
    -0.51
     negativos
    -0.50
    cill
    -0.49
    Одно
    -0.49
    مصادر
    -0.49
     betere
    -0.49
     zitate
    -0.48
     lære
    -0.47
    POSITIVE LOGITS
    WebServlet
    0.65
     disponibilités
    0.64
    IndentedString
    0.61
    kmäler
    0.58
    Personensuche
    0.58
    ConstraintMaker
    0.56
     springfox
    0.55
     indisponible
    0.54
    %
    0.53
    \{\\
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.