© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related words that express cause/effect, logic, or reasoning

    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
     But
    -0.84
    ButterKnife
    -0.76
     BUT
    -0.73
    But
    -0.72
     Nhưng
    -0.70
     lecz
    -0.70
    BUT
    -0.69
     but
    -0.66
    but
    -0.65
     lenne
    -0.63
    POSITIVE LOGITS
    ScopeManager
    0.76
    Odd
    0.64
    olden
    0.62
    opla
    0.59
     Ohr
    0.58
     Winf
    0.57
    leswig
    0.57
     Yakima
    0.56
     Skyl
    0.56
    aters
    0.56
    Activations Density 0.266%

    No Known Activations