© 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. 20-CLT-HP
    7. 78198
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act-logits · 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
     transfieras
    -0.59
    ężczy
    -0.57
     Reg
    -0.56
     JpaRepository
    -0.56
    itif
    -0.55
     SFC
    -0.55
     LoggerFactory
    -0.55
    warf
    -0.55
     TFT
    -0.54
    Diweddarwch
    -0.54
    POSITIVE LOGITS
     beat
    0.82
     beating
    0.70
    beat
    0.67
    ViewFeatures
    0.66
     beats
    0.64
     beaten
    0.59
     Beat
    0.58
     beater
    0.57
    Beat
    0.55
     stand
    0.54
    Activations Density 0.000%

    No Known Activations