© 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. 462
    Prev
    Next
    INDEX
    Explanations

    segments of text that are formatted as code or code-like content

    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
    coroutines
    -0.78
    __":
    -0.72
    WireFormatLite
    -0.71
    matchCondition
    -0.70
    DebuggerNonUser
    -0.68
    Pautan
    -0.68
    __':
    -0.68
    PhysRev
    -0.66
     للاسماء
    -0.66
    bodyParser
    -0.65
    POSITIVE LOGITS
     text
    4.44
    text
    4.34
     Text
    4.19
    Text
    3.98
     TEXT
    3.56
    TEXT
    3.55
     texts
    3.31
     Texts
    2.91
    texts
    2.83
     texto
    2.81
    Activations Density 1.752%

    No Known Activations