© 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. 20-CLT-HP
    7. 74664
    Prev
    Next
    INDEX
    Explanations

    non-english 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
    帖最后由
    -0.79
    Hozzáférés
    -0.68
    سلام
    -0.57
    findpost
    -0.55
    原始内容存档于
    -0.55
     consultato
    -0.54
    ashian
    -0.53
     biologique
    -0.52
     commerciali
    -0.51
     Dicapai
    -0.51
    POSITIVE LOGITS
     للمعارف
    0.56
     Italijanski
    0.50
     سكانية
    0.50
     delu
    0.49
    abetes
    0.49
    MessageTagHelper
    0.46
     rues
    0.45
    RegistryLite
    0.44
    Datuak
    0.42
     Affiliations
    0.42
    Activations Density 0.000%

    No Known Activations