© 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. 1-CLT-HP
    7. 456
    Prev
    Next
    INDEX
    Explanations

    consider

    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
     considéré
    -0.73
     staden
    -0.67
     isolato
    -0.67
     varandra
    -0.66
     considerato
    -0.66
     complètes
    -0.60
     seleccionados
    -0.59
     stället
    -0.59
     considerada
    -0.59
     considérée
    -0.58
    POSITIVE LOGITS
     getting
    0.82
     applying
    0.73
     using
    0.72
     creating
    0.70
     adding
    0.69
     trying
    0.68
     &___
    0.67
     implementing
    0.66
     investing
    0.65
     making
    0.65
    Activations Density 0.004%

    No Known Activations