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. 22-CLT-HP
    4. 74602
    Prev
    Next
    INDEX
    Explanations

    supplies

    np_max-act-logits · 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
     виправивши
    -0.80
    +#+#
    -0.77
     Normdatei
    -0.75
    tagHelperRunner
    -0.73
    ValueStyle
    -0.72
    errHandler
    -0.68
    IsContent
    -0.68
    TintMode
    -0.68
    ConstraintMaker
    -0.66
    fjspx
    -0.65
    POSITIVE LOGITS
    lorette
    0.50
    Q
    0.45
    th
    0.43
    Fatalf
    0.43
    Attach
    0.43
    wes
    0.43
     Buk
    0.41
    digt
    0.41
    Zan
    0.40
    instancetype
    0.40
    Activations Density 0.012%

    No Known Activations