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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3047
    Prev
    Next
    INDEX
    Explanations

    OJ

    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
     onOptions
    -0.71
     BoxDecoration
    -0.66
    setopt
    -0.64
     BorderRadius
    -0.63
    XDECREF
    -0.62
    ImageContext
    -0.60
    upsi
    -0.57
    ToRefresh
    -0.55
    VolleyError
    -0.52
     GoogleFonts
    -0.52
    POSITIVE LOGITS
    MigrationBuilder
    0.59
     <=",
    0.52
    webElementXpaths
    0.52
     poveznice
    0.48
    endete
    0.47
    PYX
    0.47
    watt
    0.45
    niająca
    0.45
     Đi
    0.45
     nema
    0.45
    Activations Density 0.004%

    No Known Activations