© 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. 94279
    Prev
    Next
    INDEX
    Explanations

    new

    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
     new
    -2.77
    new
    -2.45
     nuevos
    -2.13
     nieuwe
    -2.11
     nuevas
    -2.09
     nuovi
    -2.05
     nueva
    -1.98
     neuen
    -1.98
     nuove
    -1.95
     neue
    -1.95
    POSITIVE LOGITS
    ness
    0.96
     Zealand
    0.69
    fang
    0.68
     generation
    0.64
    sworth
    0.63
    ish
    0.61
     york
    0.59
     zealand
    0.56
    ydd
    0.56
     era
    0.54
    Activations Density 0.107%

    No Known Activations