© 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. 12-RES-MATRYOSHKA-DC
    7. 24874
    Prev
    Next
    INDEX
    Explanations

    the usage of the word "upon."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ing
    -1.00
    ING
    -0.69
     TextStyle
    -0.66
    MathML
    -0.66
    4
    -0.66
     μην
    -0.65
     Meksiku
    -0.62
    8
    -0.61
     Lombard
    -0.61
    ly
    -0.60
    POSITIVE LOGITS
    upon
    1.30
     UPON
    1.21
     upon
    1.16
     Upon
    1.10
    Upon
    1.05
     LPC
    0.93
    apis
    0.87
    estries
    0.84
     UPI
    0.82
    pidou
    0.81
    Activations Density 0.036%

    No Known Activations