© 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. 2-RES-MATRYOSHKA-DC
    7. 6634
    Prev
    Next
    INDEX
    Explanations

    questions related to the word "what"

    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
     Why
    -1.03
    Why
    -1.02
    How
    -0.83
     How
    -0.80
     Which
    -0.80
    Who
    -0.78
    Which
    -0.78
     Où
    -0.78
     Who
    -0.77
     Where
    -0.74
    POSITIVE LOGITS
     what
    0.88
     آنچه
    0.76
     something
    0.59
     everything
    0.53
    WriteTagHelper
    0.51
     quello
    0.51
     exactly
    0.50
    ViewFeatures
    0.50
     ceea
    0.50
    intu
    0.49
    Activations Density 0.086%

    No Known Activations