© 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. 4-CLT-HP
    7. 2993
    Prev
    Next
    INDEX
    Explanations

    from

    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
    rungsseite
    -0.79
    :✨
    -0.66
     fédé
    -0.63
    Démographie
    -0.62
     vérit
    -0.62
    oredCriteria
    -0.61
     wireType
    -0.61
    MigrationBuilder
    -0.60
     vectoriales
    -0.60
     Réponses
    -0.58
    POSITIVE LOGITS
     previous
    0.76
    <bos>
    0.65
     processing
    0.64
     initial
    0.62
     chemical
    0.57
    previous
    0.56
     earlier
    0.56
     making
    0.54
     recent
    0.54
     past
    0.54
    Activations Density 0.007%

    No Known Activations