© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4885
    Prev
    Next
    INDEX
    Explanations

    elements related to legal concepts involving statutes, fraudulent interests, and trust creation

    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
     poffe
    -0.69
     Efq
    -0.65
     foon
    -0.59
     Chriftian
    -0.57
     undersigned
    -0.56
     Anſ
    -0.56
    wiście
    -0.56
    principalTable
    -0.56
     justified
    -0.55
     endregion
    -0.54
    POSITIVE LOGITS
    insic
    0.55
    Contours
    0.54
    OGND
    0.51
    multicolumn
    0.50
     regardé
    0.50
    DeleteBehavior
    0.49
    usercontent
    0.49
    zzleHttp
    0.48
    ContentAsync
    0.47
    文書
    0.47
    Activations Density 0.932%

    No Known Activations