© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1311
    Prev
    Next
    INDEX
    Explanations

    This neuron seemingly detects a diverse set of keywords including coding terms, comparative language, measurements, time-related words, legal terms, and general descriptors, implying it might be identifying complex or technical writing across multiple domains. It seems to be finding language used in technical writing.

    oai_token-act-pair · gemini-2.0-flash
    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
     betweenstory
    -0.82
     beſt
    -0.67
     hanem
    -0.67
     zelve
    -0.66
     greateſt
    -0.65
    Personensuche
    -0.61
     avoient
    -0.60
     Houſe
    -0.60
     myſelf
    -0.60
     Diſ
    -0.58
    POSITIVE LOGITS
     חיצוניים
    0.81
    تقاوى
    0.69
     autorytatywna
    0.68
    PageRoute
    0.65
     שוליים
    0.65
    ,&
    0.63
    ",&
    0.63
    ValueStyle
    0.61
     pageable
    0.61
    CrossRef
    0.60
    Activations Density 6.154%

    No Known Activations