© 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. 4-CLT-HP
    7. 147
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    .
    -0.50
    indexPath
    -0.46
     wiecz
    -0.42
     émotion
    -0.40
     výbě
    -0.40
    Asi
    -0.40
    ┤
    -0.40
    DoubleClick
    -0.39
     hablando
    -0.38
    getMenuInflater
    -0.38
    POSITIVE LOGITS
    存于互联网档案馆
    0.92
    AsUp
    0.73
     mắn
    0.70
     tartalomajánló
    0.68
    kyou
    0.66
    MigrationBuilder
    0.65
    thenia
    0.64
     مشين
    0.62
    مصادر
    0.62
     Marrow
    0.61
    Activations Density 0.018%

    No Known Activations