© 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. 6-RES-MATRYOSHKA-DC
    7. 1557
    Prev
    Next
    INDEX
    Explanations

    the word "who" preceded or followed by certain pronouns and verbs

    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
     which
    -0.75
    which
    -0.75
     Merk
    -0.75
     Illuminate
    -0.73
     Pierce
    -0.73
     Stephens
    -0.71
     Augustin
    -0.71
    //}
    -0.69
    alis
    -0.68
     wich
    -0.66
    POSITIVE LOGITS
     who
    1.41
    who
    1.16
     którzy
    1.16
     Who
    1.08
     WHO
    1.08
    WHO
    1.05
    Who
    0.99
     quienes
    0.98
     quién
    0.92
     quien
    0.89
    Activations Density 0.185%

    No Known Activations