© 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. 107
    Prev
    Next
    INDEX
    Explanations

    patterns of mathematical expressions and notation

    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
    <eos>
    -0.52
    styleable
    -0.51
    dze
    -0.51
     rağmen
    -0.50
     Taschen
    -0.49
    nikom
    -0.49
    marginVertical
    -0.48
    sson
    -0.48
     때문
    -0.48
    стит
    -0.47
    POSITIVE LOGITS
    left
    4.06
     left
    3.95
     Left
    3.36
    Left
    3.31
     LEFT
    3.16
    LEFT
    3.03
    左
    2.36
     lef
    2.28
     izquierda
    2.25
    right
    2.19
    Activations Density 1.735%

    No Known Activations