© 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. 1-RES-MATRYOSHKA-DC
    7. 400
    Prev
    Next
    INDEX
    Explanations

    occurrences of code snippets involving output statements, buffer manipulations, and conditional structures in programming code

    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
     myſelf
    -1.86
     itſelf
    -1.84
     himſelf
    -1.71
     Jefus
    -1.63
     Monfieur
    -1.63
     themſelves
    -1.59
     Efq
    -1.55
     Majefty
    -1.53
     Theſe
    -1.52
     houſe
    -1.50
    POSITIVE LOGITS
    <eos>
    1.38
    .
    0.90
    ↵↵
    0.82
     
    0.77
     con
    0.71
    ↵
    0.70
     a
    0.69
     de
    0.68
     o
    0.67
    ↵↵↵↵
    0.67
    Activations Density 5.777%

    No Known Activations