© 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. 2-RES-MATRYOSHKA-DC
    7. 5033
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions, specifically those involving cosine

    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
     sin
    -1.14
     Sin
    -1.04
    Sin
    -1.02
    sin
    -0.90
     SIN
    -0.86
    SIN
    -0.79
     sine
    -0.71
    Sine
    -0.57
     Accesat
    -0.55
     Sine
    -0.52
    POSITIVE LOGITS
    cos
    2.55
    Cos
    2.16
     cos
    2.09
     Cos
    2.02
    COS
    1.73
     COS
    1.52
    cosh
    1.27
     cosine
    1.24
    cosx
    1.23
    cosine
    1.20
    Activations Density 0.017%

    No Known Activations