© 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. 2400
    Prev
    Next
    INDEX
    Explanations

    the word "than" and the phrase "instead of"

    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
     myſelf
    -1.19
     Efq
    -1.17
     itſelf
    -1.15
     Jefus
    -1.13
     auffi
    -1.11
     houſe
    -1.08
     Monfieur
    -1.07
     becauſe
    -1.05
     poffe
    -1.05
     poffible
    -1.03
    POSITIVE LOGITS
    CRETE
    0.56
     "
    0.56
     al
    0.54
     Al
    0.54
     
    0.54
     Cal
    0.53
     rus
    0.52
    ↵↵
    0.51
     Google
    0.50
     in
    0.50
    Activations Density 0.019%

    No Known Activations