© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1636
    Prev
    Next
    INDEX
    Explanations

    attributed

    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
    ing
    -1.05
    er
    -0.88
    ING
    -0.77
    e
    -0.74
    ed
    -0.73
    alities
    -0.73
     <<<<<<<<<<<<<<
    -0.68
    eration
    -0.67
     feroit
    -0.65
    erik
    -0.65
    POSITIVE LOGITS
     latter
    0.62
    IsContent
    0.60
     propOrder
    0.49
     group
    0.49
    Eloquent
    0.49
     parent
    0.49
     officially
    0.49
     former
    0.48
     permission
    0.48
    SpringBootTest
    0.48
    Activations Density 0.045%

    No Known Activations