© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12510
    Prev
    Next
    INDEX
    Explanations

    references to serialization keys in code related to object encoding and decoding

    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
    >{@
    -0.67
     sibi
    -0.61
    XMLSchema
    -0.61
    สือ
    -0.57
    Hintergrund
    -0.56
    brador
    -0.55
     بيها
    -0.55
    ffc
    -0.53
     backyard
    -0.53
     mouseClicked
    -0.53
    POSITIVE LOGITS
    ClCompile
    0.75
     forKey
    0.69
    endforeach
    0.65
    setopt
    0.65
     SPDX
    0.65
    MeasureSpec
    0.63
    TouchEvent
    0.62
     MEP
    0.62
    omials
    0.60
    WSGI
    0.59
    Activations Density 0.104%

    No Known Activations