© 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. 38948
    Prev
    Next
    INDEX
    Explanations

    guardian

    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
     consciousness
    -0.83
     consciences
    -0.71
    consciousness
    -0.70
    phany
    -0.69
     consciência
    -0.68
     noires
    -0.66
    ///</
    -0.65
     guardianship
    -0.65
    mede
    -0.65
     librement
    -0.64
    POSITIVE LOGITS
    enderror
    0.60
    TagHelper
    0.52
    ی
    0.49
     مشين
    0.49
     Paper
    0.47
    !("{}",
    0.45
     Wood
    0.44
    erie
    0.43
    bonucle
    0.43
    estad
    0.43
    Activations Density 0.024%

    No Known Activations