© 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. 48
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and structure, particularly in programming syntax

    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
    -0.86
     تكبرها
    -0.77
     Мексичка
    -0.74
     tartalomajánló
    -0.72
     estekak
    -0.71
    تقاوى
    -0.71
     linkovi
    -0.69
     мәкал
    -0.69
    OGND
    -0.67
     Италијани
    -0.66
    POSITIVE LOGITS
     
    0.52
     frame
    0.50
     main
    0.47
     reserve
    0.46
    ings
    0.46
     ACE
    0.44
     also
    0.44
     logical
    0.44
    ,
    0.44
     net
    0.44
    Activations Density 8.066%

    No Known Activations