© 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. 92153
    Prev
    Next
    INDEX
    Explanations

    lord

    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
     providers
    -0.71
     respects
    -0.59
     delivering
    -0.59
     delivers
    -0.58
    Deliver
    -0.52
    Localized
    -0.52
     Localized
    -0.52
     indietro
    -0.52
     couldn
    -0.51
     almighty
    -0.51
    POSITIVE LOGITS
    سطس
    0.69
     שוליים
    0.66
     estekak
    0.63
    uroy
    0.63
    بيوتر
    0.63
    queryInterface
    0.60
    Спољашње
    0.58
     propOrder
    0.58
    Tazama
    0.58
    contentLoaded
    0.57
    Activations Density 1.938%

    No Known Activations