© 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. 440
    Prev
    Next
    INDEX
    Explanations

    instances of the word "what" as well as "how" and "which" acting as question words

    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
    rawDesc
    -0.73
     Klee
    -0.72
    ebles
    -0.67
     közül
    -0.66
    vara
    -0.65
    例句
    -0.64
    outro
    -0.63
    OneToOne
    -0.63
     تضيفلها
    -0.63
    ើ
    -0.62
    POSITIVE LOGITS
     what
    2.92
    what
    2.83
    What
    2.81
     What
    2.78
     WHAT
    2.67
    WHAT
    2.55
    whats
    1.77
     whats
    1.76
    Whats
    1.76
     Whats
    1.56
    Activations Density 1.386%

    No Known Activations