© 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. 2-RES-MATRYOSHKA-DC
    7. 4721
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs related to data streaming and transformation, often involving specific programming patterns or keywords

    oai_token-act-pair · gpt-4.1-nano
    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
    StoryboardSegue
    -0.98
     defaultstate
    -0.85
     المعيارى
    -0.79
     vicenda
    -0.72
    thâu
    -0.70
     للمعارف
    -0.69
    ReusableCell
    -0.69
    ']")
    -0.68
    rededor
    -0.66
     Hieronymus
    -0.66
    POSITIVE LOGITS
    tado
    0.59
     understanding
    0.58
    hado
    0.54
    бла
    0.54
    zada
    0.54
    ado
    0.52
    iato
    0.52
     dat
    0.52
     overcome
    0.51
    áu
    0.51
    Activations Density 0.116%

    No Known Activations