© 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. 1472
    Prev
    Next
    INDEX
    Explanations

    code-related terms, including both assembly language directives and iOS UI element declarations

    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
    Negative Logits
    <bos>
    -1.14
    '
    -0.63
     provisoire
    -0.43
    ↵
    -0.43
    ↵↵
    -0.41
    ’
    -0.40
    1
    -0.37
    ない
    -0.37
    2
    -0.36
     mondiale
    -0.36
    POSITIVE LOGITS
     GenerationType
    2.02
    aarrggbb
    1.98
    ThroughAttribute
    1.94
    RenderAtEndOf
    1.88
    ReusableCell
    1.86
     تضيفلها
    1.85
     ProtoMessage
    1.85
     HasFactory
    1.84
     EconPapers
    1.83
    AddTagHelper
    1.80
    Activations Density 0.437%

    No Known Activations