© 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. 72
    Prev
    Next
    INDEX
    Explanations

    programming-related code structures, particularly variable declarations and method definitions

    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
    transQ
    -1.32
     betweenstory
    -1.28
     queſta
    -1.16
    AddTagHelper
    -1.14
    +#+
    -1.10
    
    -1.09
    AndEndTag
    -1.02
    extAlignment
    -1.01
    LookAnd
    -0.96
     BoxFit
    -0.96
    POSITIVE LOGITS
    (
    0.45
     (
    0.40
    0
    0.40
    data
    0.37
    1
    0.36
     I
    0.35
     ordered
    0.35
    S
    0.35
    P
    0.34
    D
    0.34
    Activations Density 13.150%

    No Known Activations