© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1308
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "much" used to express quantity or extent

    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
     NSCoder
    -0.88
    PageRoute
    -0.82
    lccn
    -0.81
     ApiException
    -0.79
    OWNER
    -0.73
    alai
    -0.73
     alphabetically
    -0.71
    LogFactory
    -0.71
    TagMode
    -0.69
     Eben
    -0.69
    POSITIVE LOGITS
     amounts
    1.22
     amount
    1.21
    amounts
    1.11
     Amounts
    1.10
     AMOUNT
    1.08
    Amount
    1.06
    amount
    1.05
     Amount
    1.05
    AMOUNT
    1.04
    Cuánto
    1.00
    Activations Density 0.479%

    No Known Activations