© 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. 1219
    Prev
    Next
    INDEX
    Explanations

    syndrome

    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
     syndrome
    -1.32
     Syndrome
    -1.17
    ngdoc
    -0.78
     síndrome
    -0.78
    ndrome
    -0.73
     employ
    -0.71
     syndromes
    -0.71
    abestanden
    -0.69
     ddelweddau
    -0.68
    HtmlAttribute
    -0.65
    POSITIVE LOGITS
     another
    0.57
    Eglise
    0.52
    ביוגרפיה
    0.52
     dozens
    0.51
     passés
    0.51
    just
    0.50
     poži
    0.50
     gesloten
    0.49
     fermés
    0.49
     overras
    0.49
    Activations Density 0.238%

    No Known Activations