© 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. 14416
    Prev
    Next
    INDEX
    Explanations

    Code or random symbols

    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
    olescence
    -0.73
    unknownFields
    -0.54
     pleaſure
    -0.50
     awakeFromNib
    -0.50
    addCriterion
    -0.48
    mtrl
    -0.48
    וויק
    -0.47
     Spisak
    -0.47
    addProperty
    -0.47
     fork
    -0.47
    POSITIVE LOGITS
    bootstrapcdn
    0.74
     بيها
    0.70
    EndContext
    0.69
    =$?
    0.63
    ècie
    0.54
    PyExc
    0.52
     يتيمه
    0.51
    tula
    0.50
    üyada
    0.50
     للاسماء
    0.49
    Activations Density 0.013%

    No Known Activations