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. 74232
    Prev
    Next
    INDEX
    Explanations

    tasting and flavors

    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
    DateTimeField
    -0.54
     rehe
    -0.52
    esgue
    -0.51
    temi
    -0.51
    therin
    -0.48
    BindView
    -0.46
    qrt
    -0.46
    cheduler
    -0.45
    feira
    -0.44
    iços
    -0.44
    POSITIVE LOGITS
     taste
    0.90
    taste
    0.79
     sample
    0.75
     مشين
    0.69
     Taste
    0.66
     eat
    0.65
    pair
    0.63
    ########.
    0.63
    sample
    0.62
     steep
    0.62
    Activations Density 0.014%

    No Known Activations