© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1974
    Prev
    Next
    INDEX
    Explanations

    afternoon

    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
    afternoon
    -0.83
    Afternoon
    -0.77
    RectangleBorder
    -0.76
     afternoon
    -0.74
     Afternoon
    -0.73
    Lunch
    -0.72
     ComVisible
    -0.64
     nakalista
    -0.64
     Baillargeon
    -0.63
     lunch
    -0.63
    POSITIVE LOGITS
    bindValue
    0.54
     Ernest
    0.51
    ArgumentParser
    0.50
    ertos
    0.48
    <
    0.48
     mergeFrom
    0.48
    BUD
    0.47
    nesses
    0.47
    ﹍﹍﹍
    0.47
     peer
    0.46
    Activations Density 0.950%

    No Known Activations