© 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. 72235
    Prev
    Next
    INDEX
    Explanations

    Code and/or foreign language

    np_max-act-logits · 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
    getSystemService
    -0.58
    itinéraire
    -0.54
    Aholisi
    -0.54
     تضيفلها
    -0.52
     Autorizaciones
    -0.51
    Kariera
    -0.51
    Население
    -0.49
     chi̍t
    -0.48
    [:,:,
    -0.48
    erializer
    -0.48
    POSITIVE LOGITS
     contextLoads
    0.70
    con
    0.66
    KURZBESCHREIBUNG
    0.56
    Referències
    0.52
     vė
    0.50
    CON
    0.49
     sánh
    0.49
    RAH
    0.48
    Fitz
    0.48
    PerformLayout
    0.46
    Activations Density 0.001%

    No Known Activations