© 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. 0-CLT-HP
    7. 42244
    Prev
    Next
    INDEX
    Explanations

    complement

    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
     increasing
    -1.25
    increasing
    -1.02
     Increasing
    -0.93
    Increasing
    -0.93
     crescente
    -0.78
     exceeding
    -0.74
     singular
    -0.71
     decreasing
    -0.71
     complement
    -0.70
     creciente
    -0.63
    POSITIVE LOGITS
    StoryboardSegue
    0.79
     Reſ
    0.78
     Diſ
    0.74
     Conſ
    0.70
    +#+#
    0.69
    ="<?=$
    0.68
     Efq
    0.68
    ✭✭
    0.68
     Inſ
    0.66
     Theſe
    0.65
    Activations Density 1.472%

    No Known Activations