© 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. 5357
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions that involve the norm of a complex vector or state, especially the squared magnitude of a certain inner product

    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
     McClure
    -0.66
     casquette
    -0.65
     affaires
    -0.59
    styleType
    -0.57
     havaianas
    -0.57
     ifrån
    -0.56
     paille
    -0.56
    cektir
    -0.56
     optimizations
    -0.56
     tecnici
    -0.55
    POSITIVE LOGITS
    |^
    2.69
    |^{
    2.63
    \|^{
    2.06
    )|^{
    1.71
    |}
    0.88
    |=
    0.82
     مشين
    0.76
    complexType
    0.75
    |=\
    0.75
    |<\
    0.74
    Activations Density 0.006%

    No Known Activations