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. 5878
    Prev
    Next
    INDEX
    Explanations

    words related to activities or hobbies, especially for children

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "practice"

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

    practice

    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
     coupable
    -0.54
    EnableWeb
    -0.54
    richTextPanel
    -0.54
     fermés
    -0.54
     emperador
    -0.52
     esternos
    -0.52
    blica
    -0.51
    Soorten
    -0.51
    infla
    -0.51
     الحره
    -0.50
    POSITIVE LOGITS
     practice
    2.69
     Practice
    2.28
    practice
    2.27
    Practice
    2.22
     PRACTICE
    2.16
     practise
    2.11
     practices
    2.00
     practiced
    1.97
     practicing
    1.96
    PRACTICE
    1.94
    Activations Density 1.836%

    No Known Activations