© 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. 6-RES-MATRYOSHKA-DC
    7. 860
    Prev
    Next
    INDEX
    Explanations

    the delta symbol, often used in mathematical or scientific notation to represent change or difference

    oai_token-act-pair · gemini-2.0-flash
    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
    OGND
    -0.89
     torchvision
    -0.75
    WebElementEntity
    -0.73
     Keene
    -0.71
    Демографія
    -0.69
     Gij
    -0.69
     functools
    -0.67
     Aene
    -0.66
     pylab
    -0.66
     commen
    -0.65
    POSITIVE LOGITS
    Delta
    1.63
     Δ
    1.63
     Delta
    1.52
    DELTA
    1.45
    Δ
    1.41
     delta
    1.40
    delta
    1.34
     DELTA
    1.27
    eltas
    1.11
     ∆
    1.05
    Activations Density 0.095%

    No Known Activations