© 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. 16388
    Prev
    Next
    INDEX
    Explanations

    negative statements or denials

    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
    arik
    -0.58
    erialize
    -0.57
    scryfall
    -0.57
     EdgeInsets
    -0.56
    ukone
    -0.56
     Hirst
    -0.55
     Coleridge
    -0.55
     williams
    -0.54
     disambiguazione
    -0.54
     Hints
    -0.51
    POSITIVE LOGITS
    存于互联网档案馆
    0.76
    modelBuilder
    0.75
    InputTagHelper
    0.73
     مشارکت‌کنندگان
    0.68
    enegger
    0.66
    panto
    0.65
     pauvres
    0.63
    testens
    0.63
    rolid
    0.63
    abelle
    0.62
    Activations Density 0.010%

    No Known Activations