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. 20-CLT-HP
    4. 74032
    Prev
    Next
    INDEX
    Explanations

    Parasites and infections

    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
     crossorigin
    -0.62
    IsMutable
    -0.61
     مشين
    -0.60
     &___
    -0.56
    \{\\
    -0.56
    KommentareTeilen
    -0.55
     Superhost
    -0.54
    ExtendWith
    -0.53
     jsPsych
    -0.52
     Ause
    -0.52
    POSITIVE LOGITS
     hel
    0.87
     hook
    0.77
     tape
    0.76
     round
    0.70
    hel
    0.69
    helm
    0.67
     worms
    0.66
     Hel
    0.65
     Tape
    0.65
     fil
    0.63
    Activations Density 0.017%

    No Known Activations