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. 73975
    Prev
    Next
    INDEX
    Explanations

    wid

    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
    HomeAsUpEnabled
    -0.67
     StringVar
    -0.64
    Jîn
    -0.64
    RegistryLite
    -0.62
    ButterKnife
    -0.57
    NgModule
    -0.57
    Personendaten
    -0.57
    таратура
    -0.57
    BagLayout
    -0.56
     ligiloj
    -0.56
    POSITIVE LOGITS
    ArrowToggle
    0.52
    sec
    0.52
     @"/
    0.47
    >{@
    0.46
    ViewData
    0.46
    ciado
    0.45
    duh
    0.44
    fjspx
    0.44
     Obrador
    0.44
    ishu
    0.44
    Activations Density 0.000%

    No Known Activations