© 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. 5-CLT-HP
    7. 4803
    Prev
    Next
    INDEX
    Explanations

    up

    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
    <bos>
    -0.63
    ChildScrollView
    -0.62
     كومونز
    -0.59
    IsContent
    -0.58
    łos
    -0.57
    stdc
    -0.54
    出版年
    -0.54
     Infórmanos
    -0.54
    mappedBy
    -0.52
    __;
    -0.52
    POSITIVE LOGITS
     tips
    0.57
     free
    0.52
     perifer
    0.50
     a
    0.49
    stretchr
    0.49
     Copy
    0.47
    tips
    0.47
    upi
    0.47
     copy
    0.46
     Camera
    0.46
    Activations Density 0.003%

    No Known Activations