© 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. 6
    Prev
    Next
    INDEX
    Explanations

    the word "and" or "or" in technical writing or diagrams

    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
     ftate
    -0.74
     Athenians
    -0.69
     Whigs
    -0.68
     firft
    -0.67
     Aton
    -0.67
     Overture
    -0.67
     sphinx
    -0.66
     Ophelia
    -0.66
     esterno
    -0.66
     Eren
    -0.66
    POSITIVE LOGITS
     and
    1.59
     And
    1.35
     AND
    1.33
     và
    1.32
    그리고
    1.30
     \&
    1.25
    Và
    1.18
    และ
    1.14
    )&&(
    1.14
     그리고
    1.13
    Activations Density 4.579%

    No Known Activations