© 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. 5-CLT-HP
    7. 92303
    Prev
    Next
    INDEX
    Explanations

    code and website data

    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
    TintMode
    -0.67
     Britons
    -0.66
    @[+][
    -0.63
     autorytatywna
    -0.60
     Soviets
    -0.59
    MLLoader
    -0.59
     Brits
    -0.58
    tanleria
    -0.58
    ulitis
    -0.56
     Lokales
    -0.56
    POSITIVE LOGITS
     élu
    0.54
     régl
    0.54
     découver
    0.52
     Arhivirano
    0.52
     soutenu
    0.51
    DebuggerNonUser
    0.50
     sélectionnés
    0.50
     personnalisés
    0.49
     publié
    0.48
     arbete
    0.48
    Activations Density 0.015%

    No Known Activations