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. 5830
    Prev
    Next
    INDEX
    Explanations

    instances of the word "start" and related words

    oai_token-act-pair · gemini-2.0-flash

    gerunds and present participles

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

    start

    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
     itſelf
    -1.20
     Efq
    -1.05
     Majefty
    -1.02
     Theſe
    -0.98
    ſelves
    -0.97
     Jefus
    -0.96
     myſelf
    -0.96
    Rhestr
    -0.96
    ^(@)
    -0.96
     Monfieur
    -0.96
    POSITIVE LOGITS
     to
    1.07
     making
    0.98
     getting
    0.90
     having
    0.88
     working
    0.85
     creating
    0.79
     using
    0.77
     doing
    0.75
     taking
    0.75
     playing
    0.75
    Activations Density 0.872%

    No Known Activations