© 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. 6-RES-MATRYOSHKA-DC
    7. 49
    Prev
    Next
    INDEX
    Explanations

    words associated with legal judgements and court proceedings

    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
     wonderful
    -0.61
     lovely
    -0.56
     kids
    -0.54
     contrast
    -0.52
     gusto
    -0.52
     amazing
    -0.51
     ideal
    -0.50
     problematic
    -0.50
    ukas
    -0.49
     excellent
    -0.49
    POSITIVE LOGITS
     '\\;'
    1.08
    GEBURTSDATUM
    0.96
     mourut
    0.90
     provisoire
    0.88
    StructEnd
    0.86
     juges
    0.85
    ItemBackground
    0.85
    setVerticalGroup
    0.84
     мәкал
    0.82
    mybatisplus
    0.82
    Activations Density 13.493%

    No Known Activations