© 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. 0-RES-MATRYOSHKA-DC
    7. 11541
    Prev
    Next
    INDEX
    Explanations

    the presence of mathematical expressions involving norms or absolute values

    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
    |^{
    -1.16
    \|^{
    -0.97
    )|^{
    -0.84
    |_{\
    -0.67
    principalTable
    -0.67
    |_{
    -0.66
    |}
    -0.60
    smithy
    -0.56
    jedis
    -0.53
    termilk
    -0.52
    POSITIVE LOGITS
    |^
    1.75
    AndEndTag
    0.68
     ویکی‌پدیای
    0.61
    rías
    0.60
    fromCharCode
    0.59
    InjectAttribute
    0.57
     Infórmanos
    0.56
    antaranya
    0.56
     gevol
    0.55
    TagMode
    0.55
    Activations Density 0.001%

    No Known Activations