© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    angle brackets and related symbols often used in programming and code

    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
    SequentialGroup
    -0.57
     dép
    -0.51
     there
    -0.49
     Te
    -0.48
    /**
    -0.48
    webElement
    -0.47
    Ξ
    -0.47
    Inherited
    -0.47
    witz
    -0.47
    medes
    -0.46
    POSITIVE LOGITS
     transfieras
    0.90
    expandindo
    0.89
    ::<
    0.86
    AsUp
    0.82
    ngdoc
    0.80
    <?,
    0.79
     nahilalakip
    0.76
    Sucesor
    0.73
    >{@
    0.71
     lenker
    0.70
    Activations Density 0.341%

    No Known Activations