© 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. 5-CLT-HP
    7. 91637
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    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
    NSMutableArray
    -0.38
    之
    -0.36
     hela
    -0.35
    chartInstance
    -0.35
     تش
    -0.35
    ett
    -0.34
    CORBA
    -0.34
    nonumber
    -0.34
     OTHERWISE
    -0.32
    scalatest
    -0.32
    POSITIVE LOGITS
     للمعارف
    0.73
    %</
    0.73
     >=",
    0.72
    %");
    0.70
    êng
    0.67
    olstein
    0.66
    ^(@)
    0.66
    ]-->
    0.66
    __);
    0.66
    %"),
    0.65
    Activations Density 0.005%

    No Known Activations