© 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. 3-RES-MATRYOSHKA-DC
    7. 2207
    Prev
    Next
    INDEX
    Explanations

    instances of the word "conserved" and related words, often in the context of scientific studies

    oai_token-act-pair · gemini-2.0-flash
    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
    +#+#
    -0.77
     Contin
    -0.77
    Stay
    -0.75
     Amat
    -0.75
     stay
    -0.71
    Stayed
    -0.71
    stay
    -0.70
     Stay
    -0.68
     Staying
    -0.68
    Staying
    -0.67
    POSITIVE LOGITS
     conserved
    2.50
     conserve
    2.28
     conservation
    2.27
     Conservation
    2.17
    conservation
    2.11
     CONSERV
    2.08
    Conservation
    2.06
     conserv
    2.02
     conserving
    1.99
     CONSERVATION
    1.91
    Activations Density 0.042%

    No Known Activations