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. 74569
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     Añade
    -0.64
    testens
    -0.56
    WebElementEntity
    -0.53
    tagHelper
    -0.52
     romanos
    -0.52
    hoppers
    -0.52
    scar
    -0.52
     وصلة
    -0.51
     industriale
    -0.51
    pandas
    -0.50
    POSITIVE LOGITS
    Jeografia
    0.57
    WriteTagHelper
    0.49
    كويكب
    0.47
    lwjgl
    0.44
     Unavailable
    0.41
    üglich
    0.40
    Spirit
    0.40
     COR
    0.40
    rister
    0.40
     ج
    0.39
    Activations Density 0.002%

    No Known Activations