© 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. 9961
    Prev
    Next
    INDEX
    Explanations

    mail

    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
     mails
    -0.75
     CreateTagHelper
    -0.72
     mail
    -0.70
     mailed
    -0.69
    Hochspringen
    -0.67
     mailbox
    -0.62
     MAIL
    -0.60
     snippetHide
    -0.60
     Mail
    -0.59
     mailing
    -0.54
    POSITIVE LOGITS
    time
    0.61
    boxes
    0.59
    camps
    0.58
    craft
    0.57
    ers
    0.56
    house
    0.55
    outs
    0.55
    houses
    0.54
    ings
    0.53
    hips
    0.53
    Activations Density 0.042%

    No Known Activations