© 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. 2-RES-MATRYOSHKA-DC
    7. 4190
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles, studies, or technical documentation

    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
    FetchType
    -0.65
    ArgumentParser
    -0.62
    niosek
    -0.59
    phos
    -0.58
     bParam
    -0.58
    FormState
    -0.58
    mybatisplus
    -0.57
    multirow
    -0.56
     nargin
    -0.56
    omla
    -0.55
    POSITIVE LOGITS
     &___
    0.64
    */),
    0.61
    RTEX
    0.59
    endregion
    0.54
    UnknownFieldSet
    0.54
    ┘
    0.53
    □
    0.53
    Demografia
    0.52
     جغرافيا
    0.52
    numeros
    0.52
    Activations Density 0.250%

    No Known Activations