© 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. 227
    Prev
    Next
    INDEX
    Explanations

    driving technology

    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
    ConstraintMaker
    -0.51
     driving
    -0.50
     дописавши
    -0.49
    hamento
    -0.48
    🖨
    -0.48
    findpost
    -0.47
    edly
    -0.47
    manship
    -0.47
    mena
    -0.47
    ortic
    -0.46
    POSITIVE LOGITS
     defaultstate
    0.75
    脚注の使い方
    0.59
    /*
    0.54
     الرياضيه
    0.54
     endforeach
    0.53
    postsleuth
    0.53
    Смотрите
    0.52
    transQ
    0.51
    vantaged
    0.51
     typelib
    0.50
    Activations Density 0.003%

    No Known Activations