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. 40834
    Prev
    Next
    INDEX
    Explanations

    PRECEDENTIAL

    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
     Efq
    -1.39
     Theſe
    -1.38
     متعلقه
    -1.27
     Monfieur
    -1.24
     Majefty
    -1.16
     myſelf
    -1.16
     initComponents
    -1.16
     Jefus
    -1.15
    bootstrapcdn
    -1.14
     $_"
    -1.13
    POSITIVE LOGITS
     "
    0.68
    .
    0.63
     on
    0.63
     (
    0.62
     and
    0.60
     as
    0.59
     “
    0.58
     in
    0.56
     or
    0.56
    ,
    0.56
    Activations Density 2.063%

    No Known Activations