© 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. 0-RES-MATRYOSHKA-DC
    7. 11644
    Prev
    Next
    INDEX
    Explanations

    the concept of an empty set or absence of elements

    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
    lesssim
    -0.84
     оригіналу
    -0.54
    ванию
    -0.51
    kozás
    -0.51
    ように
    -0.50
    itä
    -0.50
    leqslant
    -0.50
    tfrac
    -0.49
    vartheta
    -0.48
    varrho
    -0.48
    POSITIVE LOGITS
    emptyset
    2.89
    varnothing
    1.57
    ∅
    1.24
    tagHelperRunner
    0.81
    ConstraintMaker
    0.78
    MigrationBuilder
    0.77
     ब्रेकडाउन
    0.73
     ComVisible
    0.67
    />";
    0.67
    InputBorder
    0.66
    Activations Density 0.001%

    No Known Activations