© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 42507
    Prev
    Next
    INDEX
    Explanations

    kernel

    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
     output
    -1.15
     Output
    -1.01
    output
    -0.90
    )";
    
    -0.89
     whoſe
    -0.86
     Theſe
    -0.85
    Output
    -0.80
    bibfield
    -0.80
    BibitemShut
    -0.80
     Efq
    -0.79
    POSITIVE LOGITS
    ,
    0.82
    .
    0.77
     of
    0.66
     with
    0.65
    ing
    0.65
    ous
    0.65
     (
    0.65
    TagHelpers
    0.65
     and
    0.63
     for
    0.61
    Activations Density 0.090%

    No Known Activations