© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 76
    Prev
    Next
    INDEX
    Explanations

    technical terms related to experimental methods and electronic components

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.92
    tagHelperRunner
    -0.91
     ویکی‌پدی
    -0.85
     kaarangay
    -0.83
     Мексичка
    -0.79
    SourceChecksum
    -0.77
    WebElementEntity
    -0.73
    oa̍t
    -0.72
     Administrativna
    -0.71
    تقاوى
    -0.69
    POSITIVE LOGITS
    ’
    0.61
    mathrm
    0.55
    '
    0.50
    begin
    0.48
     queſto
    0.45
    lege
    0.44
    Choice
    0.44
    0.44
    kong
    0.44
    role
    0.43
    Activations Density 96.345%
    No Known Activations