© 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. 11714
    Prev
    Next
    INDEX
    Explanations

    given

    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
    脚注の使い方
    -0.63
     given
    -0.58
    下载附件
    -0.46
     chi̍t
    -0.44
    openzeppelin
    -0.44
    given
    -0.43
    "])){
    -0.43
     cref
    -0.43
    споль
    -0.43
    abestanden
    -0.42
    POSITIVE LOGITS
    ness
    0.60
     voice
    0.59
     emend
    0.54
     cytoplasm
    0.54
    makeConstraints
    0.54
     syllables
    0.54
    rated
    0.53
     Monfieur
    0.52
     prose
    0.52
     ears
    0.52
    Activations Density 0.006%

    No Known Activations