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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40816
    Prev
    Next
    INDEX
    Explanations

    I

    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
    I
    -1.64
    O
    -0.94
    T
    -0.91
     I
    -0.88
    S
    -0.85
    M
    -0.68
    t
    -0.67
    E
    -0.63
    P
    -0.63
    C
    -0.62
    POSITIVE LOGITS
     виправивши
    1.00
    +#+#
    0.97
     дописавши
    0.93
    Diweddarwch
    0.92
    AddTagHelper
    0.90
    AndEndTag
    0.89
     '\\;'
    0.88
     surla
    0.88
    writeFieldEnd
    0.85
    EDEFAULT
    0.85
    Activations Density 0.624%

    No Known Activations