© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14415
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts or the term "mathematical"

    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
    CloseOperation
    -0.88
    XmlAccessorType
    -0.81
     المعيارى
    -0.75
    principalTable
    -0.74
    Personendaten
    -0.67
    HasForeignKey
    -0.67
    GEBURTSDATUM
    -0.65
    帖最后由
    -0.65
     wireType
    -0.64
     Wicidata
    -0.62
    POSITIVE LOGITS
     Mathematical
    2.41
     mathematical
    2.36
    Mathematical
    2.02
    mathematical
    1.95
     MATHEMATICAL
    1.79
     mathematically
    1.51
     matem
    1.13
     matemática
    1.10
     Mathemat
    1.06
     mathe
    1.02
    Activations Density 0.001%

    No Known Activations