© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13775
    Prev
    Next
    INDEX
    Explanations

    references to technical features or components within software or hardware documentation

    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
     ujednoznacz
    -0.68
    setVerticalGroup
    -0.62
    Hentet
    -0.60
     allAfrica
    -0.59
     feature
    -0.55
     disponibilités
    -0.55
     onData
    -0.54
     الاطلاع
    -0.54
    PCell
    -0.52
    NullCheck
    -0.50
    POSITIVE LOGITS
    Feature
    1.57
    FEATURE
    1.22
    feature
    1.06
    Featured
    0.89
    features
    0.84
     Feature
    0.72
    Features
    0.66
    feat
    0.66
    FEAT
    0.66
    Feat
    0.65
    Activations Density 0.002%

    No Known Activations