© 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. 1-CLT-HP
    7. 14582
    Prev
    Next
    INDEX
    Explanations

    Th

    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
    RegressionTest
    -1.00
     Paglinawan
    -0.95
    脚注の使い方
    -0.81
     للاسماء
    -0.67
    AndEndTag
    -0.66
    EndGlobalSection
    -0.65
    evos
    -0.64
     للمعارف
    -0.63
     ddelweddau
    -0.61
    lapsingToolbar
    -0.60
    POSITIVE LOGITS
    springframework
    0.52
     balanceOf
    0.52
     contextLoads
    0.50
     اض
    0.47
     vastu
    0.44
    haft
    0.44
     awakeFromNib
    0.43
    ishi
    0.42
    uli
    0.42
    UITableView
    0.42
    Activations Density 0.037%

    No Known Activations