© 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. 5298
    Prev
    Next
    INDEX
    Explanations

    mentions of gardens or garden-related spaces

    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
    +#+#
    -0.65
    Supers
    -0.57
    PerformLayout
    -0.57
    AsUp
    -0.57
    Scénario
    -0.56
    enterOuterAlt
    -0.56
    ochond
    -0.56
    Cef
    -0.56
     Popcorn
    -0.55
    Glue
    -0.55
    POSITIVE LOGITS
     garden
    3.59
     Garden
    3.58
    Garden
    3.39
     GARDEN
    3.27
    garden
    3.20
     gardens
    3.02
     Gardens
    2.84
    gardens
    2.52
    GARD
    2.50
     GARD
    2.41
    Activations Density 0.017%

    No Known Activations