Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74442
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     to
    -1.59
     fallu
    -0.72
    rrggbb
    -0.62
    ();)
    -0.62
    tobe
    -0.61
    PerformLayout
    -0.61
    وردار
    -0.61
    }{*}{}
    -0.60
    VersionUID
    -0.60
    SpringBootTest
    -0.60
    POSITIVE LOGITS
     عن
    0.40
    atecas
    0.39
    RenderAtEndOf
    0.38
     Ensuring
    0.36
     oder
    0.35
     nebo
    0.34
    下载附件
    0.34
     für
    0.33
     doen
    0.33
     deff
    0.33
    Activations Density 0.001%

    No Known Activations