© 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. 1-RES-MATRYOSHKA-DC
    7. 401
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to matrix algebra and transformations

    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
    ViewBag
    -0.58
    ourage
    -0.54
    InjectAttribute
    -0.52
    mezzo
    -0.52
    тинг
    -0.50
    djangoproject
    -0.49
    spreis
    -0.49
    Pyx
    -0.48
    joba
    -0.47
    iLocal
    -0.47
    POSITIVE LOGITS
    aligned
    4.19
     aligned
    2.75
    Aligned
    2.67
     Align
    2.56
    align
    2.44
     alignment
    2.39
     align
    2.36
     ALIGN
    2.28
     Alignment
    2.27
     aligning
    2.27
    Activations Density 0.453%

    No Known Activations