© 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. 4909
    Prev
    Next
    INDEX
    Explanations

    academic/scientific publications

    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
     المعيارى
    -0.64
     indisponible
    -0.60
     controls
    -0.59
     चीज़ों
    -0.57
    tics
    -0.57
     Aras
    -0.55
    zier
    -0.55
    controls
    -0.55
    bins
    -0.54
    pii
    -0.54
    POSITIVE LOGITS
    OGND
    0.83
     ligiloj
    0.57
    IBOutlet
    0.47
     NSCoder
    0.47
     skå
    0.46
    Datuak
    0.46
     ujednoznacz
    0.44
    migrationBuilder
    0.43
    fortawesome
    0.43
    ånga
    0.42
    Activations Density 0.000%

    No Known Activations