© 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. 59
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize conditions, requirements, or instructions

    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
     ujednoznacz
    -0.92
     Италијани
    -0.85
    征詢我
    -0.74
    Tembelea
    -0.73
     uLocal
    -0.71
     CJK
    -0.70
    المناصب
    -0.70
    parsedMessage
    -0.68
     незавершена
    -0.68
    hombo
    -0.68
    POSITIVE LOGITS
    In
    0.57
    If
    0.49
     In
    0.46
    For
    0.44
     zdar
    0.42
    As
    0.41
    On
    0.41
    This
    0.40
    The
    0.40
    There
    0.39
    Activations Density 9.076%

    No Known Activations