© 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. 987
    Prev
    Next
    INDEX
    Explanations

    the word "matter," sometimes in conjunction with "of" and the definite or indefinite article

    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
     createState
    -0.76
    SYNOPSIS
    -0.67
     newBuilder
    -0.62
    sunter
    -0.59
    zzini
    -0.59
     Tubes
    -0.59
     NSCoder
    -0.59
    tagHelperRunner
    -0.57
     Wynne
    -0.57
    Sylvia
    -0.56
    POSITIVE LOGITS
     matter
    3.86
    matter
    3.47
     Matter
    3.25
    Matter
    3.22
     MATTER
    3.14
     matters
    2.84
    matters
    2.67
     Matters
    2.58
     MATTERS
    2.42
    Matters
    2.38
    Activations Density 0.075%

    No Known Activations