© 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. 6-RES-MATRYOSHKA-DC
    7. 428
    Prev
    Next
    INDEX
    Explanations

    instances of the word "change" in various contexts.

    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
     prácti
    -0.61
     McCulloch
    -0.60
     suficientes
    -0.58
    safe
    -0.58
    Literals
    -0.57
     myeloma
    -0.57
     mencapai
    -0.57
     sólidos
    -0.57
     genomen
    -0.57
     aanwezig
    -0.56
    POSITIVE LOGITS
     changes
    1.95
     Changes
    1.94
     change
    1.91
     Change
    1.86
     changing
    1.81
     changer
    1.81
     Changing
    1.79
     CHANGE
    1.79
    changes
    1.78
     changed
    1.77
    Activations Density 2.150%

    No Known Activations