© 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. 7202
    Prev
    Next
    INDEX
    Explanations

    references to voltages or voltage-related quantities

    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
     presse
    -0.69
    makeConstraints
    -0.67
    :✨
    -0.59
    setupUi
    -0.54
     press
    -0.52
     Press
    -0.52
    FieldDescriptor
    -0.52
    strains
    -0.52
     connexes
    -0.51
    akhir
    -0.51
    POSITIVE LOGITS
     voltage
    2.28
    voltage
    2.08
     Voltage
    2.06
    Voltage
    1.87
     VOLTAGE
    1.80
     voltages
    1.79
     voltaje
    1.27
    电压
    1.25
     volts
    0.88
    TAGE
    0.84
    Activations Density 0.012%

    No Known Activations