© 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. 1-CLT-HP
    7. 850
    Prev
    Next
    INDEX
    Explanations

    part

    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
    NOPQRST
    -0.63
    Scénario
    -0.60
     Wikimedijinoj
    -0.58
    corbic
    -0.53
     الرياضيه
    -0.51
    AddTagHelper
    -0.49
    vább
    -0.49
    pportun
    -0.49
     تانيه
    -0.48
    AsUp
    -0.48
    POSITIVE LOGITS
    Portail
    0.66
     contextLoads
    0.61
     createdBy
    0.59
    Datuak
    0.56
     riu
    0.51
     practised
    0.51
     killed
    0.51
    ιού
    0.50
    شهاد
    0.50
     remanded
    0.50
    Activations Density 0.006%

    No Known Activations