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. 11131
    Prev
    Next
    INDEX
    Explanations

    the word "investigation" or words with similar meanings in a political context

    oai_token-act-pair · gemini-2.0-flash

    terms signaling document transitions or new sections

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

    politics

    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
    bewerken
    -0.83
    IndentedString
    -0.73
     ProtoMessage
    -0.71
     <>",
    -0.70
     ddelweddau
    -0.69
    ✨:
    -0.68
     smtplib
    -0.64
     gyhoeddwyd
    -0.63
    Controllo
    -0.62
     '\\;'
    -0.62
    POSITIVE LOGITS
    nextLine
    0.49
     Plu
    0.44
     باز
    0.43
    off
    0.42
    amaha
    0.42
    Off
    0.41
    หว
    0.41
    NextPage
    0.41
     Púb
    0.41
    klád
    0.41
    Activations Density 3.751%

    No Known Activations