© 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. 93971
    Prev
    Next
    INDEX
    Explanations

    )

    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
     is
    -0.62
     are
    -0.50
    은
    -0.43
     has
    -0.42
    Lorem
    -0.41
     was
    -0.41
    تقاوى
    -0.41
     كومونز
    -0.40
    ectl
    -0.39
     发表于
    -0.39
    POSITIVE LOGITS
    IntoConstraints
    0.75
    Personensuche
    0.69
    NewUrlParser
    0.68
     Majefty
    0.66
     Chriftian
    0.66
    rrggbb
    0.64
    MigrationBuilder
    0.62
    StoryboardSegue
    0.62
    WebVitals
    0.62
     photolibrary
    0.62
    Activations Density 0.001%

    No Known Activations