© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13740
    Prev
    Next
    INDEX
    Explanations

    references to cellular structures involved in calcium storage and signaling, particularly the endoplasmic reticulum

    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
    propTypes
    -0.59
     doInBackground
    -0.56
     ویکی‌پدی
    -0.55
    RefNanny
    -0.54
     Corde
    -0.54
     @"/
    -0.54
    PyExc
    -0.53
    Personendaten
    -0.52
     Externe
    -0.51
    rawDesc
    -0.51
    POSITIVE LOGITS
     reticulum
    4.75
    MLLoader
    0.78
     retic
    0.77
     network
    0.69
     Network
    0.65
    Network
    0.63
     كومونز
    0.59
    network
    0.56
    ParallelGroup
    0.56
    UnknownFields
    0.56
    Activations Density 0.001%

    No Known Activations