© 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. 10390
    Prev
    Next
    INDEX
    Explanations

    biology

    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
    ValueStyle
    -0.57
    fjspx
    -0.56
    ERSHIP
    -0.56
     newBuilder
    -0.54
    +#+#
    -0.52
    ness
    -0.49
    TagHelper
    -0.49
     AssemblyCulture
    -0.49
    ategy
    -0.47
    nologies
    -0.46
    POSITIVE LOGITS
    CloseOperation
    0.56
    i
    0.55
    e
    0.54
     BorderSide
    0.54
    a
    0.50
    y
    0.50
     doInBackground
    0.49
     resistenza
    0.47
     termica
    0.47
    pore
    0.46
    Activations Density 0.018%

    No Known Activations