© 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. 6-RES-MATRYOSHKA-DC
    7. 93
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with subscripts and superscripts

    oai_token-act-pair · gemini-2.0-flash
    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
     
    -0.89
    <strong>
    -0.75
    ing
    -0.72
    ↵↵
    -0.70
     World
    -0.66
    <eos>
    -0.65
    <b>
    -0.65
    <em>
    -0.62
     “
    -0.62
     fore
    -0.61
    POSITIVE LOGITS
     ExecuteAsync
    1.23
     MonoBehaviour
    1.23
    principalColumn
    1.18
     AssemblyCulture
    1.17
    imageshack
    1.14
    resizingMask
    1.13
    AddTagHelper
    1.09
    QMetaType
    1.08
    ftagPool
    1.08
    下载附件
    1.07
    Activations Density 5.894%

    No Known Activations