© 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. 92464
    Prev
    Next
    INDEX
    Explanations

    ministerial

    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
     createState
    -0.71
    setVerticalGroup
    -0.54
    FDRE
    -0.52
    runApp
    -0.51
     Baumann
    -0.51
    ureux
    -0.47
    幕
    -0.47
     ")[
    -0.47
    IsMutable
    -0.47
    bcryptjs
    -0.46
    POSITIVE LOGITS
    DrawerToggle
    0.66
    IntoConstraints
    0.59
     presa
    0.52
    parsedMessage
    0.50
    Unset
    0.48
     TextAppearance
    0.48
    ิง
    0.47
    SaveChangesAsync
    0.46
    makeConstraints
    0.46
    LEncoder
    0.46
    Activations Density 0.006%

    No Known Activations