© 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. 2900
    Prev
    Next
    INDEX
    Explanations

    reserves

    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
     exhaustion
    -0.58
    Migrations
    -0.57
     vuitton
    -0.56
    __["
    -0.55
     Exhaus
    -0.55
     depletion
    -0.54
    roda
    -0.53
    erli
    -0.53
     cæ
    -0.52
     JADX
    -0.52
    POSITIVE LOGITS
    Personendaten
    0.72
     fast
    0.62
     faster
    0.59
     HasFactory
    0.55
     Fast
    0.52
     veloce
    0.51
    nocache
    0.50
    Fast
    0.49
     quicker
    0.49
     snabb
    0.49
    Activations Density 0.002%

    No Known Activations