© 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. 4-CLT-HP
    7. 527
    Prev
    Next
    INDEX
    Explanations

    male pronouns

    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
    '
    -0.90
    ’
    -0.75
    <bos>
    -0.73
     '\\;'
    -0.71
     CreateTagHelper
    -0.70
     linkovi
    -0.66
     AssemblyTitle
    -0.61
    /**
    -0.60
     <=",
    -0.59
     himo
    -0.56
    POSITIVE LOGITS
    thodon
    0.50
    ufel
    0.47
    солю
    0.46
    pulos
    0.46
     féminine
    0.45
    essége
    0.45
     ALI
    0.44
    uality
    0.44
    ửi
    0.43
    laş
    0.43
    Activations Density 0.007%

    No Known Activations