© 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. 14494
    Prev
    Next
    INDEX
    Explanations

    series

    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
     Series
    -1.02
    Series
    -0.96
     series
    -0.96
    series
    -0.94
     SERIES
    -0.91
    SERIES
    -0.84
     serie
    -0.77
     série
    -0.75
    série
    -0.74
     سری
    -0.71
    POSITIVE LOGITS
    $_['
    0.57
    apar
    0.56
    BeginInit
    0.55
    ########.
    0.55
     par
    0.54
     COURT
    0.50
    PerformLayout
    0.50
    gap
    0.48
    eaways
    0.48
    nocache
    0.48
    Activations Density 0.105%

    No Known Activations