© 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. 4996
    Prev
    Next
    INDEX
    Explanations

    references to legal complaints or filings

    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
     impacts
    -0.52
    ಷ
    -0.52
     Impacts
    -0.51
    macher
    -0.51
    ambilan
    -0.51
     fumée
    -0.50
     locura
    -0.49
     Bearbeit
    -0.49
    riges
    -0.49
     الدين
    -0.48
    POSITIVE LOGITS
     complaint
    2.75
     Complaint
    2.47
    complaint
    2.42
     complaints
    2.41
    Complaint
    2.23
     Complaints
    2.22
    Complaints
    2.02
     complain
    1.85
     complaining
    1.77
     complains
    1.70
    Activations Density 0.048%

    No Known Activations