© 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. 77091
    Prev
    Next
    INDEX
    Explanations

    formal writing

    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
    DockStyle
    -0.65
    المناصب
    -0.52
     endwhile
    -0.51
    Superview
    -0.50
    TintMode
    -0.50
     referenties
    -0.50
    migrationBuilder
    -0.49
    Бахар
    -0.47
    Życiorys
    -0.47
    URLException
    -0.46
    POSITIVE LOGITS
    MessageOf
    0.84
     protoimpl
    0.69
     оригіналу
    0.57
    postsleuth
    0.57
    jsxFileName
    0.56
    tiert
    0.54
    IEVE
    0.54
     ErrIntOverflow
    0.52
    vably
    0.52
     Textbook
    0.52
    Activations Density 0.000%

    No Known Activations