© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3475
    Prev
    Next
    INDEX
    Explanations

    the verb "meet."

    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
    Negative Logits
    
    -0.77
    Архівовано
    -0.74
     violation
    -0.73
    violation
    -0.66
    posedge
    -0.65
    بوابة
    -0.65
     Violation
    -0.60
     violations
    -0.59
    gegeven
    -0.57
    Kjelder
    -0.57
    POSITIVE LOGITS
     meet
    3.06
    meet
    2.84
     Meet
    2.81
     meets
    2.75
     MEET
    2.70
    Meet
    2.64
     meeting
    2.59
    MEET
    2.48
    Meeting
    2.47
     Meeting
    2.38
    Activations Density 0.049%

    No Known Activations