© 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. 0-CLT-HP
    7. 93930
    Prev
    Next
    INDEX
    Explanations

    Boo

    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
     Gro
    -0.62
     Cla
    -0.60
    tagext
    -0.59
     Sab
    -0.57
    Ārējās
    -0.55
     अलावा
    -0.55
     Gab
    -0.54
     Sh
    -0.52
    Demikian
    -0.52
    unehmen
    -0.52
    POSITIVE LOGITS
     HasFactory
    0.68
     Orrell
    0.65
     distanciation
    0.57
     UITableViewCell
    0.56
     fédé
    0.53
     defaultstate
    0.52
    BeginContext
    0.51
    flashdata
    0.50
     makeStyles
    0.50
    expandindo
    0.50
    Activations Density 1.609%

    No Known Activations