© 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. 0-CLT-HP
    7. 38355
    Prev
    Next
    INDEX
    Explanations

    unsustainable

    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
     raiſ
    -0.93
    Zeneca
    -0.89
     zoude
    -0.88
     photolibrary
    -0.88
     Majefty
    -0.85
     للاسماء
    -0.84
     poffible
    -0.84
     myſelf
    -0.84
     $_"
    -0.83
    ñores
    -0.82
    POSITIVE LOGITS
     degree
    0.49
     toe
    0.48
     grade
    0.47
     gram
    0.45
     Ex
    0.45
     use
    0.43
    themselves
    0.42
     L
    0.42
     Er
    0.42
     col
    0.41
    Activations Density 0.112%

    No Known Activations