© 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. 1-RES-MATRYOSHKA-DC
    7. 67
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions, particularly involving algebraic formulas and operations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.63
     }}</
    -0.61
    gran
    -0.54
     in
    -0.54
    )</
    -0.52
    ,</
    -0.52
     can
    -0.51
     idea
    -0.51
     or
    -0.51
    énd
    -0.51
    POSITIVE LOGITS
    *
    2.28
    !*
    1.78
     *
    1.77
    *.
    1.74
    ?*
    1.73
    )*
    1.71
    .*
    1.70
    ()*
    1.66
    *-
    1.64
    *"
    1.62
    Activations Density 3.498%

    No Known Activations