© 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. 40423
    Prev
    Next
    INDEX
    Explanations

    inhibitors

    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
     inform
    -1.16
     inhibitors
    -1.03
    h
    -1.01
    inform
    -0.93
     Inform
    -0.86
     inhibitor
    -0.83
    Inform
    -0.80
    ones
    -0.77
     informs
    -0.73
    e
    -0.71
    POSITIVE LOGITS
     Anſ
    0.80
    hyrchwyd
    0.77
     extérieures
    0.76
     scolaires
    0.76
     चीज़ों
    0.73
    oredCriteria
    0.71
     Majefty
    0.70
    %)$
    0.69
     extérieurs
    0.69
     wikipagina
    0.69
    Activations Density 0.122%

    No Known Activations