Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16710
    Prev
    Next
    INDEX
    Explanations

    the word "level"

    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
     baix
    -0.60
     Kons
    -0.59
    tectable
    -0.55
    udara
    -0.55
     Bud
    -0.53
     gezet
    -0.52
    strings
    -0.52
     Fuse
    -0.52
    Zeneca
    -0.52
     lhs
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.77
    最快更新
    0.68
    出版年
    0.67
    Hozzáférés
    0.66
    ChildScrollView
    0.65
     సౌకర్య
    0.65
    windowFixed
    0.64
    StoryboardSegue
    0.63
     Orville
    0.63
     nargin
    0.61
    Activations Density 0.010%

    No Known Activations