© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4915
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ########.
    -0.98
     ExecuteAsync
    -0.93
     ujednoznacz
    -0.91
     تضيفلها
    -0.91
    PerformLayout
    -0.88
     kasarigan
    -0.86
    ftagPool
    -0.85
    tableFuture
    -0.82
    migrationBuilder
    -0.80
     <>",
    -0.78
    POSITIVE LOGITS
     who
    0.49
     how
    0.46
    SetValue
    0.43
    :
    0.42
    m
    0.42
    nonatomic
    0.41
     most
    0.40
    <eos>
    0.39
     many
    0.39
     setting
    0.39
    Activations Density 0.000%

    No Known Activations