© 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. 1202
    Prev
    Next
    INDEX
    Explanations

    name

    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
    WebServlet
    -0.59
    subpackage
    -0.58
    كويكب
    -0.57
    IndentedString
    -0.56
     resourceCulture
    -0.54
    kina
    -0.52
    AntiForgeryToken
    -0.52
    migrationBuilder
    -0.50
    lick
    -0.50
    znac
    -0.49
    POSITIVE LOGITS
    illots
    0.49
    DispatchToProps
    0.49
    IBar
    0.48
     Dusche
    0.48
     mpl
    0.48
    dataclass
    0.47
    Obrázky
    0.47
    schedulers
    0.47
    borderSide
    0.47
    Inf
    0.45
    Activations Density 0.005%

    No Known Activations