© 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. 5-CLT-HP
    7. 3154
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
     and
    -0.65
     or
    -0.60
    even
    -0.47
    حتی
    -0.47
     mejorado
    -0.47
     beschik
    -0.46
     bahkan
    -0.46
     even
    -0.45
     Ersatz
    -0.45
    もしくは
    -0.44
    POSITIVE LOGITS
    StructEnd
    0.75
    клопе
    0.70
     one
    0.67
    MigrationBuilder
    0.64
    cendental
    0.63
    áñez
    0.58
    RTDA
    0.56
     turn
    0.56
    libft
    0.56
     fall
    0.55
    Activations Density 0.004%

    No Known Activations