© 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. 0-RES-MATRYOSHKA-DC
    7. 11036
    Prev
    Next
    INDEX
    Explanations

    neuron activated by words related to vehicles' safety devices and their housing components

    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
    例句
    -0.54
     disponibilités
    -0.52
    vernment
    -0.51
     délé
    -0.49
    UnknownFields
    -0.49
     SEÑ
    -0.49
     posa
    -0.48
    DOCUMENT
    -0.47
    كذا
    -0.47
     raggiunto
    -0.44
    POSITIVE LOGITS
     housed
    3.11
    XmlAccessorType
    0.88
     BorderSide
    0.84
     الحره
    0.82
     nahilalakip
    0.79
    WriteBarrier
    0.77
     aloj
    0.75
     encased
    0.75
    DeleteBehavior
    0.71
     виправивши
    0.70
    Activations Density 0.002%

    No Known Activations