© 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. 43617
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     Have
    -1.24
     have
    -0.77
     Be
    -0.77
     And
    -0.75
     We
    -0.75
     You
    -0.75
     To
    -0.73
     For
    -0.73
     has
    -0.72
     Do
    -0.72
    POSITIVE LOGITS
     Efq
    1.20
     Anſ
    1.13
     greateſt
    1.10
     ſeveral
    1.08
     iſt
    1.07
     snippetHide
    1.07
     itſelf
    1.05
     ſen
    1.04
     ſmall
    1.03
     ſta
    1.02
    Activations Density 0.051%

    No Known Activations