© 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. 548
    Prev
    Next
    INDEX
    Explanations

    the word "big", and to a lesser extent, words appearing near it

    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
     estekak
    -0.94
     nahilalakip
    -0.93
    findpost
    -0.90
    LookAnd
    -0.90
    fillType
    -0.90
    parsedMessage
    -0.88
    Personensuche
    -0.86
     initComponents
    -0.85
    ADELPHIA
    -0.85
     isInitialized
    -0.84
    POSITIVE LOGITS
     big
    2.75
    big
    2.44
     BIG
    2.28
    BIG
    2.14
     Big
    2.13
    Big
    2.11
     biggest
    1.61
     huge
    1.44
    biggest
    1.42
    ビッグ
    1.38
    Activations Density 0.097%

    No Known Activations