© 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. 541
    Prev
    Next
    INDEX
    Explanations

    of

    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
     الحره
    -0.85
     esternos
    -0.83
     للاسماء
    -0.81
    PerformLayout
    -0.80
     Référence
    -0.74
     surla
    -0.73
    IGraphics
    -0.69
     ligiloj
    -0.69
     Italijanski
    -0.68
    kháu
    -0.68
    POSITIVE LOGITS
     their
    0.48
     his
    0.43
    stdafx
    0.41
     all
    0.40
     that
    0.39
     my
    0.38
     junior
    0.37
    <bos>
    0.36
    paddingBottom
    0.36
     most
    0.34
    Activations Density 0.002%

    No Known Activations