© 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. 10906
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals involved in legal cases or criminal incidents

    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
     sire
    -0.48
    URU
    -0.48
    ModelAttribute
    -0.47
     شهرداری
    -0.47
    Wnd
    -0.46
     sphinct
    -0.45
     cookies
    -0.45
     Sambo
    -0.45
    ροσ
    -0.44
    Xd
    -0.44
    POSITIVE LOGITS
     Baker
    3.42
    Baker
    3.17
     BAKER
    2.73
    baker
    2.02
     baker
    1.92
     Bakers
    1.91
     bakers
    1.31
     resourceCulture
    0.96
    UnusedPrivate
    0.80
    NOPQRST
    0.77
    Activations Density 0.001%

    No Known Activations