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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12279
    Prev
    Next
    INDEX
    Explanations

    Fragments ending in "ve"

    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
     Barran
    -0.57
     Barna
    -0.57
    rivial
    -0.56
    etera
    -0.54
     arşivlendi
    -0.53
    AtIndexPath
    -0.52
    KommentareTeilen
    -0.52
    łop
    -0.52
     Perfil
    -0.51
     molecular
    -0.50
    POSITIVE LOGITS
    iness
    0.57
     unknownFields
    0.55
    /**
    0.52
    JspWriter
    0.49
    ru
    0.46
    r
    0.46
    ds
    0.45
    SuppressMessage
    0.45
    /*
    0.44
    )=>{
    0.44
    Activations Density 0.047%

    No Known Activations