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. 74251
    Prev
    Next
    INDEX
    Explanations

    Code/documentation

    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
     fieldNum
    -0.62
     يتيمه
    -0.61
    lē
    -0.56
    +#+
    -0.55
    anse
    -0.53
     Hymen
    -0.52
    AndroidJUnit
    -0.51
     Vikipedi
    -0.51
     nélkül
    -0.50
     houſe
    -0.50
    POSITIVE LOGITS
     समीक्षक
    0.60
    TypedDataSet
    0.54
    ñales
    0.45
     Krim
    0.45
    ettbewer
    0.44
    fjspx
    0.44
    riwal
    0.44
     welcome
    0.44
    RectangleBorder
    0.43
    space
    0.43
    Activations Density 0.000%

    No Known Activations