© 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. 725
    Prev
    Next
    INDEX
    Explanations

    interrogative words, especially "who", "what", "why" and "how"

    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
     Who
    -0.68
     How
    -0.63
     Why
    -0.60
    Who
    -0.58
     That
    -0.58
    addSubview
    -0.56
    ElementException
    -0.56
    ابل
    -0.55
     cré
    -0.54
    How
    -0.54
    POSITIVE LOGITS
     utafitiHapana
    0.84
     snippetHide
    0.67
     FetchType
    0.64
    CrossOrigin
    0.60
     surla
    0.57
     للمعارف
    0.57
    )];
    0.57
    ConstraintMaker
    0.56
    IsMutable
    0.56
     what
    0.55
    Activations Density 0.363%

    No Known Activations