Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74305
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    tys
    -0.56
    ATUM
    -0.53
    TestingModule
    -0.52
    IsUnicode
    -0.51
     hight
    -0.50
    tay
    -0.48
     Mancha
    -0.48
    landt
    -0.47
    slidesToShow
    -0.47
     emp
    -0.46
    POSITIVE LOGITS
    phosa
    0.68
     stället
    0.59
     fédé
    0.57
     frukt
    0.57
     financières
    0.54
     Ferrara
    0.53
     épaules
    0.53
     réguli
    0.53
    phe
    0.53
     vänner
    0.52
    Activations Density 0.000%

    No Known Activations