© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38959
    Prev
    Next
    INDEX
    Explanations

    Japanese

    np_max-act · 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
    脚注の使い方
    -0.66
     AssemblyCulture
    -0.64
    $',
    -0.62
    oredCriteria
    -0.62
     وتسجيلات
    -0.60
    FormTagHelper
    -0.58
     Alembic
    -0.58
     resourceCulture
    -0.58
     Савезне
    -0.58
     newBuilder
    -0.58
    POSITIVE LOGITS
     TimeUnit
    0.53
     Parcelable
    0.52
    nessy
    0.47
    bukkit
    0.47
    pulumi
    0.46
    hamilan
    0.46
    SpringBootTest
    0.46
    hilangan
    0.45
    sendRedirect
    0.45
     restTemplate
    0.45
    Activations Density 1.700%

    No Known Activations