© 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. 21877
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or equations, particularly involving calculations and remainders

    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
    localctx
    -0.46
    _{-\
    -0.46
     status
    -0.44
    status
    -0.44
    panou
    -0.44
    PositiveButton
    -0.43
    Geplaatst
    -0.42
     krep
    -0.42
     rung
    -0.42
    bö
    -0.42
    POSITIVE LOGITS
    #+#
    0.77
    MemoryWarning
    0.75
     GenerationType
    0.75
     typelib
    0.75
     समीक्षाओं
    0.75
    URIComponent
    0.71
     viewDidLoad
    0.66
     שוליים
    0.62
     linkovi
    0.62
     AssemblyCulture
    0.61
    Activations Density 0.131%

    No Known Activations