© 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. 1-CLT-HP
    7. 14385
    Prev
    Next
    INDEX
    Explanations

    creation and expression

    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
     recite
    -0.55
    cerely
    -0.54
     mengakui
    -0.53
    )}</
    -0.51
    zzá
    -0.50
     utafitiHapana
    -0.49
    SuppressMessage
    -0.49
    ),),
    -0.49
     Strictly
    -0.48
     kiệm
    -0.48
    POSITIVE LOGITS
     surla
    0.57
    uchter
    0.53
     trajets
    0.52
     purse
    0.51
     nahilalakip
    0.49
     Alembic
    0.48
    ArgumentParser
    0.48
    SETTINGS
    0.48
    diga
    0.47
    agem
    0.47
    Activations Density 0.130%

    No Known Activations