© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    gratitude, appreciation

    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
     bless
    -1.06
     fortunately
    -0.79
     Bless
    -0.77
     gelukkig
    -0.77
     thankfully
    -0.76
     BLESS
    -0.75
    bless
    -0.73
    脚注の使い方
    -0.72
     luckily
    -0.71
    __':
    -0.71
    POSITIVE LOGITS
    -
    0.66
     dem
    0.59
    en
    0.59
    /
    0.54
    ,
    0.54
    low
    0.52
    ade
    0.52
    dem
    0.52
     des
    0.51
     den
    0.50
    Activations Density 0.494%

    No Known Activations