© 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. 3-RES-MATRYOSHKA-DC
    7. 1236
    Prev
    Next
    INDEX
    Explanations

    text formatting and chart-like elements, sometimes found in technical documentation or data tables

    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
     ExecuteAsync
    -0.79
    sizeCache
    -0.58
    ">//
    -0.57
     pylint
    -0.55
     PackageManager
    -0.54
     PhpStorm
    -0.52
     doInBackground
    -0.52
     Normdatei
    -0.52
    ThroughAttribute
    -0.51
    TagMode
    -0.51
    POSITIVE LOGITS
     entanto
    0.83
    러나
    0.60
    ंदीखरीदारी
    0.57
     -)
    0.57
     дописавши
    0.56
    anmoins
    0.56
    ])):
    0.56
     obstante
    0.55
    XmlEnum
    0.54
    ]^{-
    0.53
    Activations Density 1.800%

    No Known Activations