© 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. 6722
    Prev
    Next
    INDEX
    Explanations

    sections of scientific or technical textual data containing structured legal citations and references

    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
     religieuses
    -0.63
    Ligações
    -0.63
     Waray
    -0.53
    Пусть
    -0.51
    adpleegd
    -0.50
     sayesinde
    -0.48
    と言っても
    -0.47
     murni
    -0.47
     lourdes
    -0.47
    뀐
    -0.46
    POSITIVE LOGITS
     BoxFit
    0.69
    Manbalar
    0.67
    >>()
    0.65
    AnchorStyles
    0.64
     Paglinawan
    0.63
     Cassini
    0.60
    ')")
    0.59
    DataAnnotations
    0.58
    saraba
    0.57
    ########.
    0.56
    Activations Density 0.178%

    No Known Activations