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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73910
    Prev
    Next
    INDEX
    Explanations

    Various topics

    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
    rungsseite
    -0.62
    webElementXpaths
    -0.54
    hier
    -0.46
    readystatechange
    -0.46
    apex
    -0.45
     Ment
    -0.45
    Digital
    -0.45
    ]^{-
    -0.45
     Digital
    -0.45
    phyllum
    -0.44
    POSITIVE LOGITS
     i
    0.68
     smart
    0.67
    IsContent
    0.65
    smart
    0.64
     cell
    0.62
    routeProvider
    0.61
    ConstraintMaker
    0.60
     phone
    0.58
    setVerticalGroup
    0.56
     سكانية
    0.56
    Activations Density 0.000%

    No Known Activations