© 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. 97487
    Prev
    Next
    INDEX
    Explanations

    words ending in "-ways"

    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
     Paglinawan
    -0.77
     runways
    -0.77
     waterways
    -0.76
    ThroughAttribute
    -0.76
     watersheds
    -0.76
     balconies
    -0.74
     mineralization
    -0.74
     chapels
    -0.72
     referenties
    -0.71
    webElementXpaths
    -0.71
    POSITIVE LOGITS
    heets
    0.64
    ystems
    0.56
    ervice
    0.56
    cape
    0.54
    pecific
    0.53
    ides
    0.52
    peed
    0.52
    heet
    0.51
    capes
    0.51
     are
    0.50
    Activations Density 0.496%

    No Known Activations