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. 74464
    Prev
    Next
    INDEX
    Explanations

    Cur

    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
    BagLayout
    -0.61
     pngtree
    -0.52
     समीक्षक
    -0.51
     NgModule
    -0.51
    WebControls
    -0.48
     habet
    -0.47
    ModelAdmin
    -0.47
    NgModule
    -0.47
    ScopeManager
    -0.46
    MethodManager
    -0.46
    POSITIVE LOGITS
    IUrlHelper
    0.66
    InjectAttribute
    0.54
     @"/
    0.53
    msgSender
    0.53
     commissioning
    0.52
     Darius
    0.50
    Einzelnachweise
    0.50
    StructEnd
    0.49
     laser
    0.48
    BufferException
    0.48
    Activations Density 0.006%

    No Known Activations