© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93559
    Prev
    Next
    INDEX
    Explanations

    diastolic

    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
     quæ
    -0.72
    __':
    -0.71
     itſelf
    -0.71
    脚注の使い方
    -0.68
    ंदीखरीदारी
    -0.67
     financieras
    -0.67
    Extinguishing
    -0.66
    IInterface
    -0.66
     виправивши
    -0.65
    e
    -0.65
    POSITIVE LOGITS
    SpringRunner
    0.47
    FormTagHelper
    0.42
    orianCalendar
    0.41
    GEBURTSDATUM
    0.41
    neu
    0.41
     numerus
    0.40
    isis
    0.40
    ism
    0.39
    return
    0.38
    lena
    0.37
    Activations Density 0.094%

    No Known Activations