© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
     would
    -0.65
     AssemblyTitle
    -0.63
    OpenHelper
    -0.63
     ujednoznacz
    -0.63
    EnableWeb
    -0.62
    AutoScaleMode
    -0.61
    NOPQRST
    -0.61
    gisi
    -0.58
    migrationBuilder
    -0.58
    Scénario
    -0.58
    POSITIVE LOGITS
    ll
    2.73
    LL
    1.93
     ll
    1.66
     LL
    1.44
    lls
    1.32
    lll
    1.30
    lla
    1.23
    Ll
    1.23
    llll
    1.16
    llr
    1.15
    Activations Density 0.032%

    No Known Activations