© 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. 11503
    Prev
    Next
    INDEX
    Explanations

    references to the historic Saxon people or their language

    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
     సౌకర్య
    -0.67
    reactstrap
    -0.63
     Signalez
    -0.60
     Rin
    -0.60
     nahilalakip
    -0.56
    الدراسه
    -0.54
    +#+#
    -0.53
    enumi
    -0.52
     بوس
    -0.52
     Superhosts
    -0.51
    POSITIVE LOGITS
    Sax
    3.19
     Sax
    3.11
     sax
    2.64
    sax
    2.45
    Saxon
    2.41
     SAX
    2.09
     Saxon
    1.99
     saxophone
    1.71
    SAX
    1.70
     Saxons
    1.59
    Activations Density 0.002%

    No Known Activations