© 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. 1959
    Prev
    Next
    INDEX
    Explanations

    mentions of federal circuit courts

    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
     itſelf
    -0.76
     Anſ
    -0.64
    seamnă
    -0.64
     Huguen
    -0.63
     NUK
    -0.63
     Tartar
    -0.63
     المعيارى
    -0.62
     Conſ
    -0.61
     doubtnut
    -0.61
     Houſe
    -0.61
    POSITIVE LOGITS
     Cir
    2.30
    Cir
    1.73
    cir
    1.27
     cir
    1.20
    PUBLISHED
    0.65
    Einzelnachweise
    0.61
     CIR
    0.61
     ProtoMessage
    0.61
     Circuit
    0.61
     –
    0.60
    Activations Density 0.035%

    No Known Activations