© 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. 389
    Prev
    Next
    INDEX
    Explanations

    coding structures, particularly functions and their parameters

    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
     vzor
    -0.54
    ambién
    -0.52
     palsu
    -0.52
    archiwizowane
    -0.48
     arşivlendi
    -0.47
     miniaturka
    -0.47
     Wikiseite
    -0.46
     bambú
    -0.45
    drawiam
    -0.44
     transparencia
    -0.44
    POSITIVE LOGITS
     referenties
    0.65
    SequentialGroup
    0.64
    __":
    0.59
     يتيمه
    0.57
    RuleContext
    0.56
    __':
    0.54
    Disliked
    0.53
    abstractmethod
    0.51
    if
    0.51
     VIDEOTAPE
    0.51
    Activations Density 0.888%

    No Known Activations