© 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. 91119
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    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
    ate
    -1.03
    ATE
    -0.88
    🏽
    -0.82
    se
    -0.82
     phrase
    -0.75
    🏾
    -0.72
    sate
    -0.71
     Shakspeare
    -0.71
     myſelf
    -0.70
     ſmall
    -0.69
    POSITIVE LOGITS
    principalTable
    0.85
    InjectAttribute
    0.77
     kaarangay
    0.76
    Personensuche
    0.76
    ьаж
    0.75
     <=",
    0.75
    IUrlHelper
    0.74
     nahilalakip
    0.73
    AndEndTag
    0.71
     Paglinawan
    0.71
    Activations Density 0.055%

    No Known Activations