© 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. 4984
    Prev
    Next
    INDEX
    Explanations

    references to specific sponge species or related scientific terms

    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
    AsUp
    -0.77
    initComponents
    -0.59
     Roscoe
    -0.59
    ksesta
    -0.58
     Matos
    -0.57
    Datuak
    -0.54
     Valdez
    -0.50
    ष्
    -0.50
     Brasile
    -0.49
     Duarte
    -0.49
    POSITIVE LOGITS
    ella
    2.58
    ell
    1.95
    elle
    1.88
    illa
    1.85
    ellas
    1.76
    ELL
    1.70
    ILLA
    1.70
    elles
    1.68
    lla
    1.66
    ellar
    1.66
    Activations Density 0.124%

    No Known Activations