Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5912
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the experience of childbirth and police searches

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "exit"

    np_token-act-pair-logits · gpt-4o-mini

    Exiting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    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
    #+#
    -0.54
     einsch
    -0.51
    InputModule
    -0.49
     consummation
    -0.48
    Abp
    -0.47
    aufnahme
    -0.46
    ufnahme
    -0.45
     <>",
    -0.45
    Климат
    -0.45
     whoſe
    -0.45
    POSITIVE LOGITS
     keluar
    1.01
     out
    0.95
     exit
    0.90
     Exit
    0.89
    Exit
    0.88
     exited
    0.88
     exiting
    0.87
     Out
    0.87
     OUT
    0.85
     EXIT
    0.85
    Activations Density 1.311%

    No Known Activations