© 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. 0-CLT-HP
    7. 43276
    Prev
    Next
    INDEX
    Explanations

    pass

    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
     passing
    -0.48
    TemporalType
    -0.47
    gnat
    -0.46
     pool
    -0.44
     SqlParameter
    -0.43
     pesce
    -0.43
     Pass
    -0.43
     particules
    -0.43
     avancé
    -0.43
     aéri
    -0.43
    POSITIVE LOGITS
     autorytatywna
    0.89
    InitVars
    0.72
    Controllo
    0.69
    :✨
    0.68
     препратки
    0.66
     shewn
    0.65
    клопе
    0.64
    Diweddarwch
    0.64
     Athenians
    0.64
    PerformLayout
    0.63
    Activations Density 0.019%

    No Known Activations