© 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. 95128
    Prev
    Next
    INDEX
    Explanations

    simple

    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
    simple
    -2.19
    simply
    -2.19
     simple
    -2.14
     simply
    -2.13
    Simply
    -2.13
     Simply
    -1.95
    Simple
    -1.85
     semplici
    -1.84
     semplice
    -1.82
     simplesmente
    -1.81
    POSITIVE LOGITS
     yet
    0.56
     enough
    0.48
     hi
    0.44
    ับ
    0.44
     number
    0.43
    math
    0.43
     "
    0.43
     to
    0.42
     picking
    0.42
    ʊ
    0.41
    Activations Density 0.061%

    No Known Activations