© 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. 1-RES-MATRYOSHKA-DC
    7. 127
    Prev
    Next
    INDEX
    Explanations

    references to multiple or many items, including quantities and multiple categories

    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
    /
    -0.65
     =
    -0.63
    er
    -0.56
    jét
    -0.56
     DFT
    -0.54
     Cassini
    -0.54
     которая
    -0.53
     eje
    -0.52
    =
    -0.52
     /
    -0.51
    POSITIVE LOGITS
     many
    2.13
     several
    1.95
     other
    1.75
    several
    1.69
     MANY
    1.69
     all
    1.65
     two
    1.63
    many
    1.63
     few
    1.62
     some
    1.61
    Activations Density 5.713%

    No Known Activations