© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95669
    Prev
    Next
    INDEX
    Explanations

    guys/people

    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
    Negative Logits
     kid
    -0.85
     guy
    -0.74
    findpost
    -0.74
    NUMX
    -0.67
     Kid
    -0.64
     تضيفلها
    -0.64
     PopupWindow
    -0.63
    kid
    -0.63
    ± 
    -0.63
    tahankan
    -0.61
    POSITIVE LOGITS
    mer
    0.69
    nier
    0.64
    line
    0.62
    ning
    0.60
    z
    0.59
    ne
    0.58
    ming
    0.58
    ned
    0.58
    nar
    0.57
    nes
    0.56
    Activations Density 0.071%

    No Known Activations