© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4573
    Prev
    Next
    INDEX
    Explanations

    mentions of specialized tools or apparatus

    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
    Method
    -0.66
     method
    -0.65
    PositiveButton
    -0.65
     ways
    -0.64
    NegativeButton
    -0.64
     Method
    -0.62
    METHOD
    -0.61
    方式
    -0.60
     METHOD
    -0.59
     Battery
    -0.57
    POSITIVE LOGITS
     equipment
    2.98
     Equipment
    2.83
    Equipment
    2.72
    equipment
    2.70
     EQUIPMENT
    2.69
     equipments
    2.33
    EQUIPMENT
    2.33
     Equip
    2.17
    equip
    1.89
     equip
    1.84
    Activations Density 0.009%

    No Known Activations