© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39990
    Prev
    Next
    INDEX
    Explanations

    words ending in "-ing"

    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
    er
    -0.59
    es
    -0.58
    ed
    -0.53
    io
    -0.48
    e
    -0.48
    ev
    -0.46
    el
    -0.45
    aj
    -0.45
    ce
    -0.45
    allo
    -0.45
    POSITIVE LOGITS
    RectangleBorder
    0.81
    CloseOperation
    0.79
    󠁿
    0.79
     وتسجيلات
    0.76
    Occurred
    0.76
     nahilalakip
    0.74
    存于互联网档案馆
    0.74
    AccessFile
    0.74
    ViewInit
    0.73
    PreferredItem
    0.73
    Activations Density 0.033%

    No Known Activations