© 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. 11114
    Prev
    Next
    INDEX
    Explanations

    prominent programming symbols and code structure indicators such as slashes and asterisks

    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
     Theſe
    -1.23
     Efq
    -1.20
     leaſt
    -1.14
     Majefty
    -1.12
     myſelf
    -1.12
     becauſe
    -1.11
     theſe
    -1.10
     ſeveral
    -1.09
     Monfieur
    -1.09
     Jefus
    -1.09
    POSITIVE LOGITS
     (
    0.68
    ,
    0.66
     in
    0.58
     S
    0.54
     .
    0.54
    U
    0.54
    <eos>
    0.53
     E
    0.53
    H
    0.52
    S
    0.52
    Activations Density 1.397%

    No Known Activations