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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91209
    Prev
    Next
    INDEX
    Explanations

    numeric digits

    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
     
    -0.48
     let
    -0.47
    <bos>
    -0.47
     me
    -0.47
    <eos>
    -0.46
     around
    -0.45
     st
    -0.45
     ma
    -0.44
     min
    -0.44
     a
    -0.43
    POSITIVE LOGITS
    WriteTagHelper
    0.94
    Personensuche
    0.88
     مرئيه
    0.82
     Wikimedijinoj
    0.79
     sumpay
    0.78
     >=",
    0.78
     فريبيس
    0.75
     otomatig
    0.74
     الحره
    0.73
    windowFixed
    0.73
    Activations Density 0.538%

    No Known Activations