© 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. 1-RES-MATRYOSHKA-DC
    7. 583
    Prev
    Next
    INDEX
    Explanations

    logical implications indicated by the word "hence."

    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
    إنه
    -0.66
    Viel
    -0.63
    IsPostBack
    -0.59
    ouchable
    -0.57
     solidity
    -0.56
     glyphicon
    -0.56
    crí
    -0.54
     Virtually
    -0.54
    EOUT
    -0.54
    那麼
    -0.54
    POSITIVE LOGITS
     hence
    4.09
    Hence
    3.64
     Hence
    3.63
    hence
    3.59
     therefore
    2.44
     thus
    2.28
    therefore
    1.98
    thus
    1.95
     portanto
    1.88
     consequently
    1.86
    Activations Density 0.012%

    No Known Activations