© 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. 71676
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    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
    Might
    -1.23
    might
    -1.15
     Might
    -1.01
    could
    -0.97
    Could
    -0.97
    Would
    -0.94
     might
    -0.93
     Could
    -0.92
     könnten
    -0.89
    would
    -0.88
    POSITIVE LOGITS
     fieldNum
    0.57
     AsyncTask
    0.51
     w
    0.51
    posedge
    0.48
    timo
    0.48
     ActiveRecord
    0.48
    DoubleQuotes
    0.47
     conjugate
    0.47
     glycogen
    0.47
     strom
    0.45
    Activations Density 0.002%

    No Known Activations