© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13673
    Prev
    Next
    INDEX
    Explanations

    window

    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
    исленность
    -0.54
    Carriera
    -0.54
     мол
    -0.51
     StatefulWidget
    -0.48
     democrática
    -0.45
    ppuden
    -0.45
    separated
    -0.44
    licherweise
    -0.44
    jalanan
    -0.44
    ctivité
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.89
    +#+#
    0.73
     resourceCulture
    0.69
    ագրություններ
    0.67
    writerow
    0.64
     esternos
    0.63
     PopupWindow
    0.57
    ViewFeatures
    0.56
    writeFieldEnd
    0.56
    /*
    0.56
    Activations Density 0.047%

    No Known Activations