© 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. 3852
    Prev
    Next
    INDEX
    Explanations

    references to specific hardware connection points, particularly identifying the pin numbers used for serial communication interfaces

    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
    textTheme
    -0.67
     Agamemnon
    -0.66
    mybatisplus
    -0.62
     تضيفلها
    -0.61
     <<<<<<<<<<<<<<
    -0.61
    usermodel
    -0.59
    tencent
    -0.58
    ValueStyle
    -0.58
    Sui
    -0.57
     Dietz
    -0.57
    POSITIVE LOGITS
     pin
    3.64
     Pin
    3.47
    Pin
    3.45
    pin
    3.30
     pins
    3.16
     PIN
    2.78
    PIN
    2.73
    pins
    2.73
     Pins
    2.69
     pinning
    2.66
    Activations Density 0.015%

    No Known Activations