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. 74256
    Prev
    Next
    INDEX
    Explanations

    technical/uncommon terms/names

    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
    PoolSize
    -0.50
    elenco
    -0.49
    mannschaft
    -0.47
    SourceChecksum
    -0.46
     lautet
    -0.46
     fixed
    -0.45
     fund
    -0.44
    aronder
    -0.44
     FIXED
    -0.44
    дя
    -0.43
    POSITIVE LOGITS
    IUrlHelper
    0.79
    ViewFeatures
    0.65
     Normdatei
    0.65
    tonsoft
    0.65
     Réponses
    0.60
    Dış
    0.58
    })));
    0.57
    IntoConstraints
    0.57
     سكانية
    0.57
     ImGui
    0.57
    Activations Density 0.000%

    No Known Activations