© 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. 2-RES-MATRYOSHKA-DC
    7. 4789
    Prev
    Next
    INDEX
    Explanations

    references to code syntax symbols and markers

    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
    })]
    -0.82
     CURIAM
    -0.79
    "](
    -0.79
    ,’”
    -0.77
     Ã
    -0.76
     Â
    -0.75
    bbene
    -0.74
    .")]
    -0.73
    )]$
    -0.72
    )».
    -0.71
    POSITIVE LOGITS
    `
    0.61
    expandindo
    0.60
    a
    0.56
     autorytatywna
    0.54
     vật
    0.53
    </code>
    0.52
    roid
    0.52
    ochim
    0.52
    agraph
    0.51
    chter
    0.51
    Activations Density 0.031%

    No Known Activations