© 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. 2-RES-MATRYOSHKA-DC
    7. 5908
    Prev
    Next
    INDEX
    Explanations

    numerical expressions related to scientific measurements and quantities

    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
     
    -0.47
    ula
    -0.42
     long
    -0.41
     I
    -0.41
     for
    -0.40
     my
    -0.40
     g
    -0.38
    Filmographie
    -0.38
     per
    -0.36
    ToServer
    -0.36
    POSITIVE LOGITS
    UnsafeEnabled
    1.28
     Мексичка
    1.19
    Geplaatst
    1.17
    IVEREF
    1.03
    webElementXpaths
    1.00
    GEBURTSDATUM
    0.99
    بوابة
    0.98
     '\\;'
    0.97
    UnusedPrivate
    0.96
     NSCoder
    0.96
    Activations Density 1.640%

    No Known Activations