© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93409
    Prev
    Next
    INDEX
    Explanations

    savings

    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
     saving
    -2.20
     savings
    -2.06
    saving
    -1.98
    Saving
    -1.97
     Saving
    -1.95
     Savings
    -1.79
    savings
    -1.75
     SAVINGS
    -1.70
    Savings
    -1.67
     saved
    -1.62
    POSITIVE LOGITS
    aarrggbb
    0.69
     digress
    0.55
     tartalomajánló
    0.54
    commodations
    0.49
     eclipse
    0.47
     chutes
    0.46
     Antonia
    0.46
     generalizations
    0.45
     betweenstory
    0.45
    Trusted
    0.45
    Activations Density 0.147%

    No Known Activations