© 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. 2-RES-MATRYOSHKA-DC
    7. 7222
    Prev
    Next
    INDEX
    Explanations

    sections of code or text containing formatting symbols, including comments and code structure markers

    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
    PointerException
    -0.82
    AccessFile
    -0.61
    原始内容存档于
    -0.60
     Pula
    -0.60
    yntaxException
    -0.60
    kring
    -0.58
    toBeTruthy
    -0.57
    sendRedirect
    -0.57
     Provinz
    -0.56
    anglès
    -0.56
    POSITIVE LOGITS
    httphttps
    0.60
     intptr
    0.55
    _
    0.54
     تضيفلها
    0.52
    AutoScale
    0.51
     restoran
    0.50
    WithIOException
    0.49
    BeginContext
    0.47
    довлет
    0.47
     uitges
    0.46
    Activations Density 0.656%

    No Known Activations