© 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. 904
    Prev
    Next
    INDEX
    Explanations

    this

    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
     >=",
    -0.66
     виправивши
    -0.63
    Vidite
    -0.60
     насељу
    -0.57
    참고
    -0.57
    onOptions
    -0.56
    tagHelper
    -0.56
    ilever
    -0.54
     betweenstory
    -0.53
    onAttach
    -0.53
    POSITIVE LOGITS
     cliquer
    0.50
    keyColumn
    0.48
     bedingt
    0.47
    erçe
    0.46
    alogie
    0.46
     preuve
    0.45
    omorphism
    0.45
    MeasureSpec
    0.45
    searchResults
    0.45
    tasche
    0.44
    Activations Density 0.019%

    No Known Activations