© 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. 94940
    Prev
    Next
    INDEX
    Explanations

    ventricle

    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
    jsxFileName
    -0.67
    DockStyle
    -0.56
    OrNil
    -0.54
    NUMX
    -0.54
     ?>/
    -0.52
    
    -0.51
     مواليد
    -0.50
     ویکی‌پدیای
    -0.49
     Normdatei
    -0.48
    InjectAttribute
    -0.48
    POSITIVE LOGITS
     lenker
    0.53
     صوتيه
    0.52
    المناصب
    0.52
    ecap
    0.52
    例文
    0.51
    rylic
    0.48
    ethe
    0.47
    ec
    0.46
     loadImage
    0.46
    ungle
    0.45
    Activations Density 0.003%

    No Known Activations