© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38998
    Prev
    Next
    INDEX
    Explanations

    period

    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
     The
    -0.98
     This
    -0.86
     It
    -0.84
    AndEndTag
    -0.83
     These
    -0.83
    ↵↵
    -0.82
     Those
    -0.82
     However
    -0.81
     CreateTagHelper
    -0.81
     There
    -0.79
    POSITIVE LOGITS
     she
    0.57
     her
    0.54
     well
    0.52
     of
    0.51
     first
    0.50
     on
    0.49
     an
    0.47
     the
    0.46
     all
    0.46
     one
    0.46
    Activations Density 0.632%

    No Known Activations