© 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. 96019
    Prev
    Next
    INDEX
    Explanations

    government

    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
     trust
    -0.86
     trusted
    -0.82
    trust
    -0.82
    Trust
    -0.80
     Trust
    -0.79
     trustworthy
    -0.77
     affid
    -0.75
     trusting
    -0.72
     TRUST
    -0.72
     trusts
    -0.68
    POSITIVE LOGITS
    fhir
    0.66
    WireFormatLite
    0.63
     >=",
    0.62
     bezeichneter
    0.61
     jScrollPane
    0.60
    CodedInputStream
    0.60
     refusé
    0.60
     ChromeDriver
    0.60
     Convex
    0.59
     précisé
    0.58
    Activations Density 0.005%

    No Known Activations