© 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. 3-RES-MATRYOSHKA-DC
    7. 1292
    Prev
    Next
    INDEX
    Explanations

    the word "who"

    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
     people
    -1.05
     Menschen
    -0.92
    people
    -0.91
     human
    -0.88
     which
    -0.85
    People
    -0.84
     humans
    -0.84
    PEOPLE
    -0.83
     människor
    -0.82
     mensen
    -0.80
    POSITIVE LOGITS
     who
    1.99
    who
    1.83
     Who
    1.70
    Who
    1.62
     WHO
    1.55
    WHO
    1.54
     którzy
    1.38
     quién
    1.27
     quien
    1.24
     whom
    1.21
    Activations Density 0.124%

    No Known Activations