© 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. 2-RES-MATRYOSHKA-DC
    7. 5926
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and programming constructs

    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
     nemlig
    -0.77
     up
    -0.77
    uxxxx
    -0.71
    Grüsse
    -0.68
    
    -0.68
     <<<<<<<<<<<<<<
    -0.67
    󠁣
    -0.65
     down
    -0.65
     initComponents
    -0.64
     Waray
    -0.64
    POSITIVE LOGITS
    out
    1.88
    OUT
    1.65
    Out
    1.28
    outs
    1.20
     Out
    0.98
    Output
    0.97
    アウト
    0.95
     OUT
    0.91
    output
    0.90
    Outs
    0.90
    Activations Density 0.020%

    No Known Activations