© 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. 92317
    Prev
    Next
    INDEX
    Explanations

    current events

    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
    }^{+}$
    -0.54
    uens
    -0.51
    erva
    -0.50
    upta
    -0.49
    orce
    -0.47
    anah
    -0.47
    /}
    -0.46
     чему
    -0.46
    __;
    -0.45
    erit
    -0.44
    POSITIVE LOGITS
    <bos>
    1.43
    脚注の使い方
    0.86
    UnusedPrivate
    0.85
    IUrlHelper
    0.82
     '\\;'
    0.78
    expandindo
    0.78
    BeginContext
    0.77
    IsContent
    0.77
     disambiguazione
    0.75
     дописавши
    0.74
    Activations Density 0.108%

    No Known Activations