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. 1-CLT-HP
    4. 12840
    Prev
    Next
    INDEX
    Explanations

    Harry Potter or combustion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.76
     Homer
    -0.70
    Homer
    -0.65
    omotor
    -0.60
    ::~
    -0.59
    ChildScrollView
    -0.58
     Potter
    -0.55
    AsUp
    -0.53
    Potter
    -0.52
     combustion
    -0.49
    POSITIVE LOGITS
    Vidite
    0.73
     InputDecoration
    0.64
    Brainz
    0.57
    urlencoded
    0.55
    ẳng
    0.53
    neath
    0.52
    RuleContext
    0.50
    出版年
    0.50
     Certo
    0.50
     AssemblyCulture
    0.49
    Activations Density 0.007%

    No Known Activations