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. 0-CLT-HP
    4. 13
    Prev
    Next
    INDEX
    Explanations

    Femininity & elegance

    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
     ſeveral
    -1.00
     ſtate
    -0.96
     trasparente
    -0.95
     raiſ
    -0.94
     Jefus
    -0.93
     deſt
    -0.93
     Monfieur
    -0.92
     Efq
    -0.91
     himſelf
    -0.90
     purpoſe
    -0.90
    POSITIVE LOGITS
    s
    0.94
     Ch
    0.55
     J
    0.53
     block
    0.51
    sä
    0.51
     dat
    0.51
     local
    0.50
     const
    0.50
     Block
    0.49
     Inc
    0.49
    Activations Density 1.142%

    No Known Activations