© 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. 93912
    Prev
    Next
    INDEX
    Explanations

    happiness

    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
    <bos>
    -0.48
    asca
    -0.47
    fromnode
    -0.46
    uxxxx
    -0.41
     vedi
    -0.41
    örper
    -0.40
     nash
    -0.40
     kenn
    -0.39
     ModelExpression
    -0.39
     nas
    -0.39
    POSITIVE LOGITS
    IndentedString
    0.75
    gelöst
    0.70
     for
    0.65
    Panamoan
    0.63
     teaching
    0.63
    argout
    0.61
     rijk
    0.60
    انتهای
    0.60
    QMetaType
    0.59
     wireType
    0.58
    Activations Density 0.002%

    No Known Activations