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. 74399
    Prev
    Next
    INDEX
    Explanations

    technical text snippets

    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
    <bos>
    -0.59
    MemoryWarning
    -0.57
    getMock
    -0.55
     Portail
    -0.54
     Thrones
    -0.53
    InitVars
    -0.52
    følgelig
    -0.51
     NDEBUG
    -0.50
     JAXBElement
    -0.49
     resourceCulture
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.60
     referrerpolicy
    0.53
    المكان
    0.52
    grapher
    0.50
    PLATE
    0.49
     مر
    0.49
    plate
    0.48
    transporter
    0.47
    dorfer
    0.46
    vika
    0.46
    Activations Density 0.023%

    No Known Activations