© 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. 6716
    Prev
    Next
    INDEX
    Explanations

    references to electronic interactions and properties

    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
     electronic
    -0.98
     Electronic
    -0.96
    Electronic
    -0.91
    electronic
    -0.88
     ELECTRONIC
    -0.75
     elektronik
    -0.64
     electrónicos
    -0.64
     digital
    -0.58
     صوتيه
    -0.57
    electronics
    -0.55
    POSITIVE LOGITS
     electron
    2.30
     Electron
    1.95
    electron
    1.86
    Electron
    1.77
     electrons
    1.58
    ctrons
    1.23
    electrons
    1.13
     ELECTRON
    0.83
     UnityEditor
    0.78
     viewDid
    0.76
    Activations Density 0.008%

    No Known Activations