© 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. 1-RES-MATRYOSHKA-DC
    7. 236
    Prev
    Next
    INDEX
    Explanations

    references to groups of people

    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
    AddHtmlAttribute
    -0.84
     childs
    -0.76
    NameInMap
    -0.75
    EndGlobalSection
    -0.75
     AssemblyCulture
    -0.72
     Prussian
    -0.71
     Hons
    -0.70
    IntoConstraints
    -0.69
    structors
    -0.69
    __.__
    -0.68
    POSITIVE LOGITS
     people
    4.13
    people
    3.75
    People
    3.66
     People
    3.58
     PEOPLE
    3.28
    PEOPLE
    2.91
     mensen
    2.50
     ppl
    2.44
     pessoas
    2.39
     peoples
    2.30
    Activations Density 1.144%

    No Known Activations