© 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. 535
    Prev
    Next
    INDEX
    Explanations

    the word "assume" and related words

    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
     Bracken
    -0.84
     posteriore
    -0.75
     McLaugh
    -0.70
     pathlib
    -0.69
    clearTimeout
    -0.69
     BDS
    -0.69
     '\\;'
    -0.69
    :`
    -0.67
     sentiments
    -0.66
     giudi
    -0.66
    POSITIVE LOGITS
     assume
    2.13
     assumption
    1.86
     assumed
    1.84
     assumes
    1.83
     assuming
    1.82
    assume
    1.80
     Assume
    1.77
     Assumptions
    1.75
     assumptions
    1.73
    assumed
    1.65
    Activations Density 0.171%

    No Known Activations