© 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. 4-CLT-HP
    7. 49
    Prev
    Next
    INDEX
    Explanations

    register

    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
     EconPapers
    -0.71
    StructEnd
    -0.71
    IntoConstraints
    -0.66
    SBATCH
    -0.63
    aarrggbb
    -0.63
    :✨
    -0.63
     <=",
    -0.61
     للاسماء
    -0.61
    +:+
    -0.59
     dAtA
    -0.59
    POSITIVE LOGITS
     could
    0.75
     would
    0.75
     might
    0.72
    <bos>
    0.72
     will
    0.68
     Could
    0.67
     can
    0.66
     have
    0.65
     Would
    0.65
     are
    0.65
    Activations Density 0.005%

    No Known Activations