© 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. 2-RES-MATRYOSHKA-DC
    7. 3353
    Prev
    Next
    INDEX
    Explanations

    idiomatic expressions related to making use of opportunities or gaining advantage

    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
    </blockquote>
    -0.49
     rendus
    -0.48
    gemeen
    -0.45
     собой
    -0.42
     ...
    -0.42
    veux
    -0.42
    timus
    -0.42
    значно
    -0.42
    ่าง
    -0.41
     computadora
    -0.40
    POSITIVE LOGITS
    SharedDtor
    0.94
     الرياضيه
    0.87
    parsedMessage
    0.85
    IsContent
    0.81
     متعلقه
    0.79
     HasFactory
    0.77
    FieldBuilder
    0.77
    شهاد
    0.75
    SourceChecksum
    0.75
     Lordships
    0.74
    Activations Density 0.323%

    No Known Activations