© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1280
    Prev
    Next
    INDEX
    Explanations

    the word "go" followed by certain prepositions

    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
     skrzy
    -0.84
    GEBURTSDATUM
    -0.84
     ję
    -0.81
    ſelves
    -0.81
     whoſe
    -0.78
     anhänger
    -0.76
    āra
    -0.75
     Theſe
    -0.74
     reaſon
    -0.73
     tört
    -0.71
    POSITIVE LOGITS
     go
    1.66
     going
    1.46
     goes
    1.37
     Going
    1.36
     went
    1.35
    Going
    1.34
     Go
    1.33
    Went
    1.31
    Go
    1.30
    Goes
    1.30
    Activations Density 0.319%

    No Known Activations