Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39278
    Prev
    Next
    INDEX
    Explanations

    words ending in "ized"

    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
    ized
    -1.71
    ised
    -1.02
    izing
    -0.94
    less
    -0.79
    ization
    -0.79
    IZED
    -0.77
    ed
    -0.77
    ened
    -0.76
    izes
    -0.76
    ize
    -0.70
    POSITIVE LOGITS
    AndEndTag
    1.05
    GEBURTSDATUM
    1.00
    OGND
    0.85
    batore
    0.84
    WriteTagHelper
    0.84
    اریخ
    0.83
     TextAppearance
    0.81
     كومونز
    0.80
    ImageContext
    0.80
    bewerken
    0.79
    Activations Density 0.152%

    No Known Activations