© 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. 12259
    Prev
    Next
    INDEX
    Explanations

    references to structured programming constructs and data types in 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
    expandindo
    -0.70
     consultato
    -0.68
    sweet
    -0.61
     useEffect
    -0.59
     vPvB
    -0.59
     Sweet
    -0.57
     FetchType
    -0.57
    ymce
    -0.56
    --)
    -0.56
    inheritDoc
    -0.55
    POSITIVE LOGITS
    HMAC
    0.72
     Additions
    0.71
    jons
    0.68
     reckon
    0.67
     Barnett
    0.65
    Nah
    0.65
     wits
    0.63
    onie
    0.63
    Additions
    0.63
     Emanuel
    0.61
    Activations Density 0.071%

    No Known Activations