© 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. 2-RES-MATRYOSHKA-DC
    7. 3062
    Prev
    Next
    INDEX
    Explanations

    references to biological or chemical properties, specifically noting when properties or behaviors of molecules, structures, or substances are demonstrated or exemplified

    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
    Eksterne
    -0.75
    arbonato
    -0.72
    pung
    -0.66
     المعيارى
    -0.62
    口气
    -0.60
    ++
    -0.60
    })$}
    -0.60
     SimpleName
    -0.59
    IOUtils
    -0.59
     condic
    -0.59
    POSITIVE LOGITS
     exhibit
    2.28
     exhibits
    2.13
     Exhibit
    1.98
     Exhibits
    1.87
    Exhibit
    1.73
     exhibiting
    1.71
     EXHIBIT
    1.70
     exhibited
    1.66
     exhibition
    1.59
     EXHIB
    1.57
    Activations Density 0.009%

    No Known Activations