© 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. 2804
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical and measurement data related to study design, treatment doses, and experimental parameters

    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
    Portale
    -0.72
    ']}
    -0.71
    mapStateToProps
    -0.68
     doInBackground
    -0.66
    Bae
    -0.63
     noqa
    -0.62
    clectic
    -0.61
     JpaRepository
    -0.61
    extAlignment
    -0.61
    ViewImports
    -0.60
    POSITIVE LOGITS
     bedingt
    0.60
    dotenv
    0.53
     dû
    0.53
    kendo
    0.53
     зв
    0.51
     montón
    0.50
     akibat
    0.50
     caused
    0.49
     Polícia
    0.47
    caused
    0.47
    Activations Density 0.174%

    No Known Activations