© 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. 42764
    Prev
    Next
    INDEX
    Explanations

    )/

    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
    /
    -1.37
    )/
    -1.02
    ./
    -1.01
     /
    -0.85
    ]/
    -0.82
    %/
    -0.79
    }/
    -0.79
     and
    -0.77
    /$
    -0.73
    /(
    -0.71
    POSITIVE LOGITS
     itſelf
    0.90
     Beſ
    0.81
     ―――――
    0.80
    ſelf
    0.78
     Anſ
    0.78
     purpoſe
    0.77
    WebVitals
    0.76
     Cæsar
    0.73
     ſeveral
    0.73
    ſelves
    0.72
    Activations Density 0.226%

    No Known Activations