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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74258
    Prev
    Next
    INDEX
    Explanations

    is

    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
     propOrder
    -1.00
    RectangleBorder
    -0.94
     AssemblyCulture
    -0.93
    setVerticalGroup
    -0.92
    InputBorder
    -0.91
    DockStyle
    -0.91
     StringTokenizer
    -0.90
    GEBURTSDATUM
    -0.89
    \{\\
    -0.89
     AttributeSet
    -0.86
    POSITIVE LOGITS
     to
    0.50
     c
    0.46
    c
    0.42
     found
    0.41
     the
    0.38
    ")[
    0.36
    да
    0.35
     named
    0.35
     as
    0.33
    &&
    0.33
    Activations Density 0.001%

    No Known Activations