© 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. 96116
    Prev
    Next
    INDEX
    Explanations

    introductory phrases

    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
     uncertainties
    -0.51
     sufficiency
    -0.50
    numberOfLines
    -0.50
    caref
    -0.50
    CreateModel
    -0.50
    othed
    -0.50
     obscurity
    -0.50
     definit
    -0.48
     Niro
    -0.48
     convin
    -0.48
    POSITIVE LOGITS
     called
    0.65
     appelé
    0.56
    CloseOperation
    0.56
     sold
    0.56
     appelée
    0.55
     mères
    0.55
     usata
    0.54
     utilisée
    0.52
     used
    0.52
     known
    0.52
    Activations Density 0.002%

    No Known Activations