© 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. 4-CLT-HP
    7. 4687
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    ेशा
    -0.50
     onView
    -0.45
    grees
    -0.43
    UES
    -0.42
    survi
    -0.42
    niająca
    -0.41
     GenerationType
    -0.40
    preter
    -0.40
    भी
    -0.39
    Pře
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.73
    TextHelper
    0.71
    DrawerToggle
    0.69
     venons
    0.69
     متعلقه
    0.66
    Portale
    0.66
     للمعارف
    0.65
    thâu
    0.64
    WriteBarrier
    0.63
    lapsingToolbar
    0.62
    Activations Density 0.001%

    No Known Activations