© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1564
    Prev
    Next
    INDEX
    Explanations

    is

    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
     فريبيس
    -1.01
    Personendaten
    -0.88
    OGND
    -0.87
    UrlResolution
    -0.87
     تضيفلها
    -0.85
    ConstraintMaker
    -0.83
    ArrowToggle
    -0.82
    enderror
    -0.82
    SourceChecksum
    -0.81
    twimg
    -0.79
    POSITIVE LOGITS
    setHorizontal
    0.51
     the
    0.50
     an
    0.43
     a
    0.42
     lâ
    0.41
    HECK
    0.40
    shtml
    0.40
     noexcept
    0.40
     double
    0.40
     calientes
    0.40
    Activations Density 0.004%

    No Known Activations