© 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. 0-CLT-HP
    7. 43264
    Prev
    Next
    INDEX
    Explanations

    The word "better"

    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
     better
    -0.71
    Better
    -0.71
    better
    -0.66
     Better
    -0.65
     Res
    -0.60
    uhn
    -0.54
     von
    -0.50
     improved
    -0.49
    rese
    -0.48
    Res
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.91
     betweenstory
    0.89
    expandindo
    0.88
     nahilalakip
    0.82
    IntoConstraints
    0.79
    parsedMessage
    0.79
     propOrder
    0.79
     MainAxisSize
    0.79
    awtextra
    0.78
     فريبيس
    0.76
    Activations Density 1.076%

    No Known Activations