© 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. 351
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to programming and computation

    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
    Negative Logits
     ſch
    -0.52
     ſche
    -0.50
    ticularly
    -0.50
    ſelves
    -0.49
     Verſ
    -0.48
     userModel
    -0.45
     leſs
    -0.44
     SafeMath
    -0.44
    พาะ
    -0.44
     Shakspeare
    -0.44
    POSITIVE LOGITS
     then
    0.87
     subsequently
    0.86
     thereafter
    0.82
     afterward
    0.79
     afterwards
    0.77
     vervolgens
    0.77
     سپس
    0.76
     násled
    0.75
     затем
    0.72
     następnie
    0.72
    Activations Density 5.815%

    No Known Activations