© 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. 15376
    Prev
    Next
    INDEX
    Explanations

    age

    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
     povol
    -0.51
    additive
    -0.47
     küpe
    -0.47
    ájá
    -0.46
     hű
    -0.46
     kuiten
    -0.46
     régi
    -0.45
    crime
    -0.45
     lærer
    -0.45
     sû
    -0.45
    POSITIVE LOGITS
     RoutedEventArgs
    0.93
    uxxxx
    0.91
    consulté
    0.80
     '\\;'
    0.78
    rrggbb
    0.78
    ChildScrollView
    0.77
    addPreferredGap
    0.76
     NSCoder
    0.75
    Datuak
    0.75
     CYTHON
    0.74
    Activations Density 0.060%

    No Known Activations