© 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. 72938
    Prev
    Next
    INDEX
    Explanations

    in

    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
    rawDesc
    -0.87
    MigrationBuilder
    -0.85
    InjectAttribute
    -0.84
    windowFixed
    -0.80
    HasAnnotation
    -0.79
    writeFieldEnd
    -0.78
     виправивши
    -0.75
    
    -0.75
     Places
    -0.75
    protoimpl
    -0.75
    POSITIVE LOGITS
    lo
    0.45
     quality
    0.43
    ez
    0.43
     set
    0.42
    zec
    0.41
     z
    0.41
    Lue
    0.40
    有
    0.40
    iez
    0.40
     stad
    0.39
    Activations Density 0.002%

    No Known Activations