© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13345
    Prev
    Next
    INDEX
    Explanations

    references to specific types of biological detection methods or experimental techniques

    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
    Buck
    -0.54
     fiscales
    -0.50
     Municipalidad
    -0.50
    buc
    -0.50
     Buck
    -0.48
     Khalil
    -0.48
     rodea
    -0.46
     bæ
    -0.46
     shipper
    -0.46
     APPELLANT
    -0.45
    POSITIVE LOGITS
     blo
    3.47
     Blo
    3.00
    blo
    2.84
    Blo
    2.66
     BLO
    2.02
    BLO
    1.73
     bloke
    1.09
    blox
    1.08
    blooming
    0.99
     Blooming
    0.98
    Activations Density 0.015%

    No Known Activations