© 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. 19427
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific terms and symbols related to equations and functions

    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
    TRIP
    -0.52
     Metropolitana
    -0.52
    recruit
    -0.48
    França
    -0.48
    ymce
    -0.47
    ыгана
    -0.46
     Dobson
    -0.45
    mbda
    -0.44
     Recruitment
    -0.44
     recruitment
    -0.44
    POSITIVE LOGITS
     مشين
    0.90
    MessageTagHelper
    0.82
     NSCoder
    0.82
    ToAction
    0.70
     насељу
    0.69
    DataAnnotations
    0.69
    UnitTesting
    0.69
    IsContent
    0.68
    endphp
    0.68
    #+#
    0.67
    Activations Density 0.313%

    No Known Activations