© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12304
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and functions, particularly those involving exponents and variables

    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
     Orrell
    -1.04
     שוליים
    -1.02
     Jefus
    -0.99
     fubject
    -0.94
    WriteBarrier
    -0.93
     itſelf
    -0.93
     auffi
    -0.92
     parseFrom
    -0.92
     ProtoMessage
    -0.91
     pinulongan
    -0.90
    POSITIVE LOGITS
    ^{
    1.34
    }^{
    0.86
     Willoughby
    0.78
     ^{
    0.75
    __.
    0.69
    )^{
    0.68
    ))^{
    0.66
    LOGGER
    0.66
    })^{
    0.65
     Kyo
    0.65
    Activations Density 0.134%

    No Known Activations