© 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. 5-CLT-HP
    7. 1048
    Prev
    Next
    INDEX
    Explanations

    serious

    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
     opérateur
    -0.56
     pedagogical
    -0.55
    ArrowToggle
    -0.54
    ugo
    -0.52
     ddelweddau
    -0.51
     marito
    -0.49
    ürm
    -0.49
     propOrder
    -0.49
     hydrostatic
    -0.49
    زاری
    -0.48
    POSITIVE LOGITS
    Бахар
    0.69
     about
    0.62
    PYX
    0.55
     насељу
    0.54
     About
    0.50
    السكان
    0.50
    About
    0.48
     Normdatei
    0.48
    下载附件
    0.47
    saraba
    0.47
    Activations Density 0.003%

    No Known Activations