© 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. 4-CLT-HP
    7. 324
    Prev
    Next
    INDEX
    Explanations

    breathing

    np_max-act · gemini-2.0-flash
    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
     promozione
    -0.47
     responsável
    -0.46
     sää
    -0.44
     pensato
    -0.43
     Walling
    -0.43
     responsáveis
    -0.42
     henkilö
    -0.40
    ectado
    -0.40
     jossa
    -0.40
     traseiro
    -0.40
    POSITIVE LOGITS
    +#+#
    0.87
     المعيارى
    0.76
     وتسجيلات
    0.75
    urlpatterns
    0.70
     nakalista
    0.69
     OMITBAD
    0.69
     NSCoder
    0.66
     Drapeau
    0.66
     تعدى
    0.64
    Chham
    0.64
    Activations Density 0.001%

    No Known Activations