© 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. 1850
    Prev
    Next
    INDEX
    Explanations

    am

    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
     am
    -2.59
     Am
    -1.38
    Am
    -1.21
    am
    -0.91
     AM
    -0.83
     is
    -0.77
     are
    -0.77
     can
    -0.73
     I
    -0.72
     my
    -0.69
    POSITIVE LOGITS
     Efq
    1.38
     CreateTagHelper
    1.28
     Anſ
    1.26
     Majefty
    1.24
     ainfi
    1.24
     pleaſure
    1.24
     himſelf
    1.23
     purpoſe
    1.23
    CloseOperation
    1.23
     greateſt
    1.23
    Activations Density 0.542%

    No Known Activations