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. 12924
    Prev
    Next
    INDEX
    Explanations

    component

    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
    -0.81
     Monfieur
    -0.77
    createStatement
    -0.73
     houſe
    -0.71
     raiſ
    -0.68
     createState
    -0.67
     Normdatei
    -0.67
     Houſe
    -0.66
     defaultstate
    -0.64
     getItemCount
    -0.64
    POSITIVE LOGITS
    таратура
    0.51
    queryInterface
    0.43
     External
    0.43
    External
    0.42
    aze
    0.42
     anemia
    0.41
    bital
    0.41
     Ta
    0.41
     fale
    0.41
     ta
    0.40
    Activations Density 0.120%

    No Known Activations