© 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. 3-RES-MATRYOSHKA-DC
    7. 635
    Prev
    Next
    INDEX
    Explanations

    the capitalized word "Delta" or the symbol $\Delta$.

    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
    Демографія
    -0.75
    TintMode
    -0.75
    ьаж
    -0.73
    OGND
    -0.73
    whip
    -0.69
     commen
    -0.68
     CURIAM
    -0.67
    WireFormat
    -0.67
    Cork
    -0.66
     Cork
    -0.66
    POSITIVE LOGITS
    Delta
    2.73
     Delta
    2.38
     Δ
    2.19
    Δ
    2.11
     delta
    2.02
    DELTA
    1.96
     DELTA
    1.86
    ∆
    1.78
     ∆
    1.77
    delta
    1.63
    Activations Density 0.060%

    No Known Activations