© 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. 5-CLT-HP
    7. 92178
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
    SourceChecksum
    -0.74
     @}
    -0.73
     EClass
    -0.60
     MTC
    -0.60
     للاسماء
    -0.58
    IUrlHelper
    -0.57
     Comprometido
    -0.55
    ècie
    -0.55
    SharedDtor
    -0.54
    ItemBackground
    -0.54
    POSITIVE LOGITS
     weaker
    0.67
     fewer
    0.66
     shorter
    0.63
     smaller
    0.61
     Shorter
    0.55
     shallo
    0.53
     flatter
    0.53
     Smaller
    0.53
     farther
    0.52
     Vikipedi
    0.52
    Activations Density 0.005%

    No Known Activations