© 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. 20-CLT-HP
    7. 76893
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · 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
    quels
    -0.86
     οποία
    -0.75
    which
    -0.74
     οποίο
    -0.73
    Which
    -0.72
     hvilke
    -0.72
    quelles
    -0.71
     quale
    -0.71
     cuales
    -0.69
     hvem
    -0.68
    POSITIVE LOGITS
     that
    2.66
    that
    0.91
     bahwa
    0.90
     که
    0.80
     rằng
    0.79
     dass
    0.77
     что
    0.72
     że
    0.67
     että
    0.66
     कि
    0.65
    Activations Density 0.002%

    No Known Activations