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. 74535
    Prev
    Next
    INDEX
    Explanations

    code

    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
     المعيارى
    -0.79
     оригіналу
    -0.77
    ftagPool
    -0.76
    ✨:
    -0.71
    enderror
    -0.65
    adpleegd
    -0.59
    EndContext
    -0.59
    jmniej
    -0.58
    JAKARTA
    -0.58
    presso
    -0.58
    POSITIVE LOGITS
     cream
    0.45
     tan
    0.43
    illoma
    0.43
    llan
    0.42
     viață
    0.42
    ell
    0.41
    templateUrl
    0.41
     laid
    0.41
    opho
    0.41
     pendek
    0.41
    Activations Density 0.004%

    No Known Activations