© 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. 96139
    Prev
    Next
    INDEX
    Explanations

    these/those

    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
     CreateTagHelper
    -0.71
    RectangleBorder
    -0.68
     Between
    -0.66
    Дереккөздер
    -0.65
     transfieras
    -0.63
    Between
    -0.63
     الرياضيه
    -0.63
     وتسجيلات
    -0.62
    ⓧ
    -0.61
    PerformLayout
    -0.61
    POSITIVE LOGITS
     two
    0.81
     three
    0.72
     several
    0.64
     different
    0.62
     various
    0.60
     verschillende
    0.54
     separate
    0.52
     four
    0.52
     seemingly
    0.50
     component
    0.49
    Activations Density 0.002%

    No Known Activations