© 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. 90
    Prev
    Next
    INDEX
    Explanations

    code/text formatting

    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
     autorytatywna
    -0.54
     ran
    -0.51
     run
    -0.48
     चीज़ों
    -0.48
     pretend
    -0.47
    toHaveBeenCalled
    -0.47
    ISTS
    -0.46
     oprot
    -0.45
     runs
    -0.45
    شا
    -0.44
    POSITIVE LOGITS
     Extragalactic
    0.68
     AppColors
    0.63
    InputBorder
    0.59
    مصادر
    0.57
    FieldBuilder
    0.56
     Seti
    0.55
     the
    0.54
    RTGC
    0.54
    \{\\
    0.54
    RTLR
    0.53
    Activations Density 0.007%

    No Known Activations