© 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. 3957
    Prev
    Next
    INDEX
    Explanations

    references to personal or private information

    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
     personally
    -0.77
     Himself
    -0.62
     personalities
    -0.62
     myself
    -0.57
     himself
    -0.57
     personality
    -0.56
     Personally
    -0.56
    ędz
    -0.55
    AddTagHelper
    -0.54
     yourselves
    -0.53
    POSITIVE LOGITS
    Personal
    1.01
     Personal
    0.97
    personal
    0.87
    EndGlobalSection
    0.79
     personal
    0.79
     personales
    0.64
     PERSONAL
    0.63
     виправивши
    0.63
    ."],
    0.60
     مرئيه
    0.58
    Activations Density 0.006%

    No Known Activations