© 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. 9619
    Prev
    Next
    INDEX
    Explanations

    everybody/everyone

    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
     Everybody
    -0.64
    Everybody
    -0.59
     Everyone
    -0.56
    everyone
    -0.51
    everybody
    -0.51
    Everyone
    -0.50
    brador
    -0.49
     is
    -0.48
     jsPsych
    -0.48
    aarrggbb
    -0.47
    POSITIVE LOGITS
     arent
    0.60
     aren
    0.59
     AssemblyCulture
    0.56
     cref
    0.55
    ly
    0.55
    DebuggerNonUser
    0.54
    Referanser
    0.52
     UITableViewCell
    0.51
    efois
    0.51
    InlineData
    0.50
    Activations Density 0.233%

    No Known Activations