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. 11117
    Prev
    Next
    INDEX
    Explanations

    multiple sclerosis

    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
    はじめに
    -0.56
    gimento
    -0.55
     Perfon
    -0.54
     gynhyrchwyd
    -0.53
    StoryboardSegue
    -0.50
     Eſ
    -0.49
     通販
    -0.49
     Inſ
    -0.48
     Anſ
    -0.47
     Rout
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.72
    OuterClass
    0.56
     Haller
    0.53
    XmlAccessType
    0.53
     FormBuilder
    0.53
    uxley
    0.51
    المناصب
    0.51
     blanches
    0.50
    tagext
    0.49
    Portály
    0.49
    Activations Density 0.080%

    No Known Activations