© 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. 94470
    Prev
    Next
    INDEX
    Explanations

    Expressing doubt

    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
     arbete
    -0.54
     eneste
    -0.52
     prossima
    -0.52
     mahdol
    -0.50
     lucru
    -0.50
    tvguidetime
    -0.49
     innehåller
    -0.47
    次は
    -0.47
     eingeführt
    -0.47
    ču
    -0.47
    POSITIVE LOGITS
     whether
    0.99
     StatelessWidget
    0.84
    SourceChecksum
    0.83
    TagMode
    0.73
     '\\;'
    0.71
    MessageOf
    0.71
    PerformLayout
    0.69
     how
    0.67
     that
    0.65
     intptr
    0.65
    Activations Density 0.002%

    No Known Activations