© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12097
    Prev
    Next
    INDEX
    Explanations

    references to version control systems, specifically "git" and its variants

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
     politics
    -0.53
     co
    -0.51
    titure
    -0.50
     byen
    -0.49
     Loading
    -0.47
     repo
    -0.46
     Spon
    -0.45
    protoimpl
    -0.45
    repo
    -0.44
     halben
    -0.44
    POSITIVE LOGITS
     git
    2.14
     Git
    1.27
    Git
    0.94
    PMailer
    0.79
     EconPapers
    0.77
    ########.
    0.75
     GIT
    0.70
     дописавши
    0.68
    ngdoc
    0.64
     protoimpl
    0.60
    Activations Density 0.001%

    No Known Activations