© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11087
    Prev
    Next
    INDEX
    Explanations

    the presence of various combinations of conjunctions and associated terms in research contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.73
     autorytatywna
    -0.69
    BagLayout
    -0.64
     nocturne
    -0.62
    especie
    -0.61
     שוליים
    -0.59
    Diwedd
    -0.57
    Boas
    -0.57
     estekak
    -0.56
     חיצוניים
    -0.56
    POSITIVE LOGITS
    sizeCache
    0.66
    таратура
    0.52
    ValueGenerated
    0.47
    WireFormatLite
    0.46
    AddHtmlAttribute
    0.45
    sez
    0.42
     farsi
    0.41
    Péri
    0.41
    protoimpl
    0.41
    rentice
    0.40
    Activations Density 0.149%

    No Known Activations