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. 22-CLT-HP
    4. 74328
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · 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
    titleMargin
    -0.81
    出版年
    -0.75
    GEBURTSDATUM
    -0.73
    xtures
    -0.71
     ägg
    -0.70
     mãos
    -0.69
     Италијани
    -0.68
     AssemblyProduct
    -0.68
    IsMutable
    -0.67
    fjspx
    -0.66
    POSITIVE LOGITS
    providedIn
    0.43
     opening
    0.42
    nodoc
    0.38
    WriteLiteral
    0.38
    ouden
    0.36
    yor
    0.35
    dern
    0.34
     very
    0.34
     I
    0.34
    atorship
    0.34
    Activations Density 0.001%

    No Known Activations