© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13575
    Prev
    Next
    INDEX
    Explanations

    references to names of specific individuals, likely identifying them

    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
    GeneratedValue
    -0.58
     BioLib
    -0.55
    Бахар
    -0.55
    kháu
    -0.54
     Vise
    -0.53
     별
    -0.52
    StreetMap
    -0.51
     Ashes
    -0.51
     Selamat
    -0.51
     Patsy
    -0.50
    POSITIVE LOGITS
     Lopez
    2.14
    Lopez
    1.77
     López
    1.75
     lopez
    1.48
    López
    1.11
     lópez
    0.95
     nicotine
    0.81
     незавершена
    0.62
     Adic
    0.60
     Logan
    0.56
    Activations Density 0.002%

    No Known Activations