© 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. 7337
    Prev
    Next
    INDEX
    Explanations

    references to legal decisions or judgments

    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
     county
    -1.00
    county
    -0.94
     County
    -0.93
     COUNTY
    -0.88
     counties
    -0.81
    County
    -0.79
    COUNTY
    -0.67
     Counties
    -0.65
    ardians
    -0.55
     states
    -0.54
    POSITIVE LOGITS
     State
    1.07
    UserScript
    0.85
    State
    0.85
    tagHelperRunner
    0.74
    ंदीखरीदारी
    0.72
    Portail
    0.71
    urlpatterns
    0.67
     packageName
    0.67
     fileSize
    0.65
     endIndex
    0.64
    Activations Density 0.034%

    No Known Activations