© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 554
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fine" indicating a focus on the concept of quality or precision

    oai_token-act-pair · gpt-4.1-nano
    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
    AddHtmlAttribute
    -0.64
    TagHelpers
    -0.57
     createSprite
    -0.57
    Успе
    -0.56
     Erfol
    -0.54
     Baptiste
    -0.54
     répon
    -0.53
    PHPExcel
    -0.52
    RTLR
    -0.52
    ujudkan
    -0.52
    POSITIVE LOGITS
     fine
    5.13
    fine
    4.69
    Fine
    4.69
     Fine
    4.47
     FINE
    4.25
    FINE
    3.77
     finer
    3.03
     fines
    2.73
    fines
    2.45
     Fines
    2.41
    Activations Density 0.163%

    No Known Activations