© 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. 11425
    Prev
    Next
    INDEX
    Explanations

    mentions of 'uber' or 'Uber', likely indicating the neuron is detecting references to the company Uber or the concept of something being "uber" in a metaphorical sense

    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
     Ber
    -1.17
    Ber
    -0.97
     sickness
    -0.84
     Berge
    -0.82
     ivelany
    -0.76
     Berthe
    -0.75
    出版年
    -0.73
    клопе
    -0.72
    StoryboardSegue
    -0.72
     Sickness
    -0.71
    POSITIVE LOGITS
    bers
    1.39
    ber
    1.04
    BERS
    0.94
    BER
    0.93
    uber
    0.69
     فريبيس
    0.59
    bered
    0.59
     مشين
    0.55
    бер
    0.54
    ایج
    0.51
    Activations Density 0.003%

    No Known Activations