© 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. 40214
    Prev
    Next
    INDEX
    Explanations

    product

    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
    ChildScrollView
    -0.58
     da
    -0.52
     di
    -0.52
     tim
    -0.51
    ')->
    -0.51
     “
    -0.50
     nh
    -0.49
     pers
    -0.49
     ke
    -0.48
     sen
    -0.48
    POSITIVE LOGITS
     itſelf
    0.77
     uſed
    0.73
     pleaſure
    0.73
     myſelf
    0.72
     purpoſe
    0.70
     himſelf
    0.69
     raiſ
    0.69
     desnuda
    0.67
     chapels
    0.67
     vastaan
    0.67
    Activations Density 0.041%

    No Known Activations