© 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. 5-CLT-HP
    7. 845
    Prev
    Next
    INDEX
    Explanations

    The

    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
    Билгалдахарш
    -1.02
    ⓧ
    -0.73
    RegressionTest
    -0.71
     дописавши
    -0.69
    脚注の使い方
    -0.69
     Erişim
    -0.69
    లాలు
    -0.65
    ఔ
    -0.64
     numerus
    -0.63
    esez
    -0.60
    POSITIVE LOGITS
     pleasure
    0.68
     privilege
    0.65
     honor
    0.61
     honour
    0.55
     good
    0.55
     brilliant
    0.51
     great
    0.50
     fortunate
    0.47
     amazing
    0.47
     amaz
    0.47
    Activations Density 0.005%

    No Known Activations