© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    code snippets or structures related to optional or repeated data fields in code or data models

    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
    UnusedPrivate
    -0.94
     Majefty
    -0.91
     houſe
    -0.89
    neſs
    -0.85
     Efq
    -0.85
    GEBURTSDATUM
    -0.84
    AsUp
    -0.83
     Houſe
    -0.82
    parsedMessage
    -0.82
    ſelf
    -0.79
    POSITIVE LOGITS
     _
    3.34
    (_
    2.23
     (_
    2.16
    =_
    2.09
    ,_
    1.87
     [_
    1.85
    [_
    1.81
    :_
    1.80
    ._
    1.74
    >(_
    1.68
    Activations Density 0.152%

    No Known Activations