© 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. 912
    Prev
    Next
    INDEX
    Explanations

    code snippets that make extensive use of underscores

    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
    Geplaatst
    -0.92
    parsedMessage
    -0.87
    ConstraintMaker
    -0.86
     للمعارف
    -0.83
     itſelf
    -0.81
    )");
    -0.80
     Jefus
    -0.77
    MemoryWarning
    -0.77
    примеча
    -0.77
     viewDidLoad
    -0.76
    POSITIVE LOGITS
     _
    1.95
    ._
    1.91
     __
    1.64
    (_
    1.51
     (_
    1.46
    =_
    1.46
    /_
    1.38
    ->_
    1.34
    ?_
    1.34
    ::_
    1.30
    Activations Density 0.275%

    No Known Activations