© 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. 3-RES-MATRYOSHKA-DC
    7. 2047
    Prev
    Next
    INDEX
    Explanations

    code that uses the word "context."

    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
     jLabel
    -0.84
    GEBURTSDATUM
    -0.84
    ✨:
    -0.82
    featureID
    -0.80
     ویکی‌پدی
    -0.71
    webElementXpaths
    -0.69
    mobileqq
    -0.69
    gradle
    -0.69
    MultipartFile
    -0.68
     Commencez
    -0.67
    POSITIVE LOGITS
     context
    3.28
    context
    3.22
     Context
    3.09
    Context
    3.06
     contexts
    2.81
     CONTEXT
    2.78
    CONTEXT
    2.67
     contexto
    2.41
    contexts
    2.36
    ctx
    2.28
    Activations Density 0.091%

    No Known Activations