© 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. 96315
    Prev
    Next
    INDEX
    Explanations

    min

    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
     préférences
    -0.59
    expandindo
    -0.58
    Parity
    -0.57
     Wend
    -0.56
    ferm
    -0.56
     Sensing
    -0.56
    contentLoaded
    -0.55
     怎样
    -0.55
    ập
    -0.54
    glasses
    -0.54
    POSITIVE LOGITS
    WaitGroup
    0.60
    достатки
    0.51
     ویکی‌پدیا
    0.46
    Consequently
    0.44
    writeField
    0.44
     कीजिए
    0.42
    XtraEditors
    0.42
    وفاته
    0.41
    ConstraintMaker
    0.41
    MultipartFile
    0.40
    Activations Density 0.008%

    No Known Activations