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. 74358
    Prev
    Next
    INDEX
    Explanations

    NER

    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
     سكانية
    -0.61
     InputDecoration
    -0.58
    BufferException
    -0.56
     ویکی‌پدیا
    -0.52
     مواليد
    -0.52
     plau
    -0.50
    cuno
    -0.50
     déclarations
    -0.49
     civile
    -0.49
    dsa
    -0.47
    POSITIVE LOGITS
     utafitiHapana
    0.67
    HasAnnotation
    0.66
    MIDDLEWARE
    0.60
    googleapis
    0.50
    XmlAccessorType
    0.49
     Privile
    0.48
    usercontent
    0.48
    Privile
    0.46
     Pole
    0.45
     appliance
    0.45
    Activations Density 0.001%

    No Known Activations