© 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
    2. Gemma-2-2B
    3. 1-RES-MATRYOSHKA-DC
    4. 112
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" or similar coordinating words

    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
     fubject
    -0.86
     ftate
    -0.86
    tagHelper
    -0.79
     caufe
    -0.79
     purpoſe
    -0.79
     Aton
    -0.77
     fuper
    -0.73
     poffible
    -0.71
     occaf
    -0.71
     ſta
    -0.71
    POSITIVE LOGITS
     and
    2.91
    and
    1.80
     AND
    1.77
     And
    1.76
     và
    1.75
     \&
    1.65
    และ
    1.59
     и
    1.56
     그리고
    1.55
     και
    1.47
    Activations Density 5.045%

    No Known Activations