© 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. 3-RES-MATRYOSHKA-DC
    7. 2813
    Prev
    Next
    INDEX
    Explanations

    the names of United States judicial circuits

    oai_token-act-pair · gemini-2.0-flash
    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
     autorytatywna
    -0.83
     myſelf
    -0.81
     Efq
    -0.78
     circulaire
    -0.77
     itſelf
    -0.76
     Nimbus
    -0.75
     Shakspeare
    -0.74
     Socrates
    -0.73
     MonoBehaviour
    -0.73
     himſelf
    -0.71
    POSITIVE LOGITS
     Circuit
    1.91
    Circuit
    1.61
     CIRCUIT
    1.48
     circuit
    1.46
    circuit
    1.38
     Circuits
    0.96
     circuits
    0.93
    CUIT
    0.88
     circuito
    0.75
    cuit
    0.73
    Activations Density 0.009%

    No Known Activations