© 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. 6477
    Prev
    Next
    INDEX
    Explanations

    references to business entities and their transactions

    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
     Мексичка
    -0.84
     Италијани
    -0.71
     незавершена
    -0.68
     étoit
    -0.66
     HttpNotFound
    -0.65
    IVEREF
    -0.65
    CORBA
    -0.65
    InvalidProtocol
    -0.64
     ThemeData
    -0.64
    writeFieldEnd
    -0.61
    POSITIVE LOGITS
    @[+][
    0.42
    coltura
    0.39
    ContextHolder
    0.38
     colonias
    0.38
    CompanyName
    0.37
     <-
    0.37
    amsmath
    0.37
    ⁡
    0.37
    نسي
    0.36
     Segments
    0.36
    Activations Density 0.450%

    No Known Activations