© 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. 1-CLT-HP
    7. 8728
    Prev
    Next
    INDEX
    Explanations

    Pok/pok

    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
     Pok
    -0.65
    Pok
    -0.56
    AndEndTag
    -0.55
    olla
    -0.50
     FormGroup
    -0.47
     Sui
    -0.47
     inoxidable
    -0.47
     oprot
    -0.47
    rzost
    -0.46
     CWE
    -0.45
    POSITIVE LOGITS
    Източници
    0.58
    รก
    0.57
    tagHelperRunner
    0.53
     transfieras
    0.53
    bray
    0.53
    stande
    0.52
    reshold
    0.49
    twimg
    0.49
    ranton
    0.48
    acles
    0.48
    Activations Density 0.157%

    No Known Activations