© 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. 1-CLT-HP
    7. 14539
    Prev
    Next
    INDEX
    Explanations

    they

    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
     are
    -1.47
     were
    -1.03
     aren
    -0.92
    are
    -0.89
     have
    -0.87
     weren
    -0.85
     seem
    -0.85
     ARE
    -0.84
     arent
    -0.81
     deserve
    -0.76
    POSITIVE LOGITS
     is
    1.09
     has
    0.77
    was
    0.75
     isn
    0.75
     was
    0.71
     Is
    0.71
    has
    0.70
     Was
    0.70
     Has
    0.69
    檚
    0.69
    Activations Density 0.015%

    No Known Activations