© 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. 5-CLT-HP
    7. 2316
    Prev
    Next
    INDEX
    Explanations

    code

    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
    BeginContext
    -0.61
    BufferException
    -0.59
    begriff
    -0.56
     елның
    -0.54
    rabble
    -0.54
     snippetHide
    -0.52
    Források
    -0.52
    JspWriter
    -0.52
    elter
    -0.49
     vacacionales
    -0.49
    POSITIVE LOGITS
    ValueStyle
    0.81
    <()>
    0.57
    asInstanceOf
    0.54
    principalTable
    0.52
    oneph
    0.50
    dyti
    0.50
    isEqual
    0.48
     VIAF
    0.48
     Reiche
    0.48
    ক্ত
    0.48
    Activations Density 0.001%

    No Known Activations