© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13826
    Prev
    Next
    INDEX
    Explanations

    the presence of specific technical or coded symbols, identifiers, or labels

    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
    parsedMessage
    -1.19
    contentLoaded
    -1.13
    StoryboardSegue
    -1.08
    Personendaten
    -1.02
     initComponents
    -0.97
    SourceChecksum
    -0.92
    MigrationBuilder
    -0.91
     ZE
    -0.89
    WebElementEntity
    -0.89
     nahilalakip
    -0.87
    POSITIVE LOGITS
    z
    0.95
    Z
    0.90
    ěj
    0.48
     lò
    0.46
    x
    0.46
     spē
    0.46
    ux
    0.44
    Пря
    0.43
    ribu
    0.42
    rox
    0.42
    Activations Density 0.020%

    No Known Activations