© 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. 2646
    Prev
    Next
    INDEX
    Explanations

    the word "plaintiff"

    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
     defensi
    -0.75
    --){
    -0.69
     externi
    -0.69
    devices
    -0.68
     Bela
    -0.67
    MCM
    -0.66
     MCM
    -0.63
     فريبيس
    -0.63
     betweenstory
    -0.62
     éclair
    -0.60
    POSITIVE LOGITS
     plaintiff
    1.98
     Plaintiff
    1.81
    Plaintiff
    1.81
     plaintiffs
    1.72
     Plaintiffs
    1.51
     PLAINTIFF
    1.41
     PLAINT
    0.96
    plain
    0.83
    PLAINT
    0.82
     lawsuit
    0.80
    Activations Density 0.018%

    No Known Activations