© 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. 94904
    Prev
    Next
    INDEX
    Explanations

    lives

    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
    ⓧ
    -0.77
     fond
    -0.50
    <bos>
    -0.50
     Gries
    -0.49
    Rüyada
    -0.49
    :✨
    -0.47
     ke
    -0.46
    lives
    -0.46
     fast
    -0.46
    groovy
    -0.46
    POSITIVE LOGITS
     ApiException
    0.65
    rrggbb
    0.61
     FetchType
    0.59
     smtplib
    0.58
    titleMargin
    0.57
    Хьажоргаш
    0.55
    TEMPO
    0.54
    MenuInflater
    0.52
    PMID
    0.49
     pylori
    0.49
    Activations Density 0.000%

    No Known Activations