© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or comparisons

    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
    Negative Logits
     AssemblyCulture
    -0.65
    SharedDtor
    -0.65
    sizeCache
    -0.62
     propOrder
    -0.61
    InvalidProtocol
    -0.60
     MenuView
    -0.59
    oredCriteria
    -0.59
    :✨
    -0.57
    Viitteet
    -0.57
     AssemblyProduct
    -0.57
    POSITIVE LOGITS
    ioutil
    0.66
    isometric
    0.54
    akaian
    0.54
    Bronnen
    0.53
     hvil
    0.51
    Liefs
    0.50
     Acon
    0.49
    qrst
    0.48
    ổng
    0.46
    Groetjes
    0.46
    Activations Density 0.021%

    No Known Activations