© 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. 4803
    Prev
    Next
    INDEX
    Explanations

    expressions involving the floor function with a constant coefficient, often indicating an interest in quantized or discretized mathematical bounds

    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
     kích
    -0.54
    pond
    -0.54
     vege
    -0.53
    &&\
    -0.52
     ماز
    -0.50
    ále
    -0.47
    vega
    -0.47
    ABOVE
    -0.47
     investigate
    -0.47
    wens
    -0.47
    POSITIVE LOGITS
    rfloor
    5.44
    rceil
    3.06
    ⌋
    1.76
    lfloor
    1.45
    rangle
    1.03
    ⌊
    0.92
    rrbracket
    0.91
     AssemblyCompany
    0.90
    ⌉
    0.88
    FTFY
    0.84
    Activations Density 0.006%

    No Known Activations