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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16217
    Prev
    Next
    INDEX
    Explanations

    second person pronouns, especially with conditional clauses

    oai_token-act-pair · gemini-2.0-flash

    you

    np_token-act-pair-logits · gemini-2.0-flash

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    AndEndTag
    -0.80
     <<<<<<<<<<<<<<
    -0.70
    DeleteBehavior
    -0.66
    CreateMap
    -0.62
    oredCriteria
    -0.61
    adpleegd
    -0.57
    ѝ
    -0.55
    hoeddwyd
    -0.55
    createCanvas
    -0.55
    toHaveBeenCalled
    -0.54
    POSITIVE LOGITS
    Ծանոթ
    0.52
    hdashline
    0.47
    dengar
    0.46
     sportiva
    0.44
    เดิน
    0.42
     setTitle
    0.42
    Assista
    0.42
    Nguồn
    0.42
    iempos
    0.41
    masin
    0.40
    Activations Density 0.868%

    No Known Activations