© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14172
    Prev
    Next
    INDEX
    Explanations

    overlapping

    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
     overlapping
    -1.08
     overlapped
    -0.98
    lapping
    -0.98
     overlap
    -0.96
    overlapping
    -0.93
    overlap
    -0.81
     overlaps
    -0.80
     overla
    -0.60
    MemoryWarning
    -0.60
    Overlap
    -0.59
    POSITIVE LOGITS
     Jed
    0.59
    tagHelperRunner
    0.56
     succeeding
    0.54
    Tud
    0.52
     bedro
    0.52
     مفص
    0.52
    Jed
    0.50
     Accesat
    0.49
    rigen
    0.47
     internetowa
    0.47
    Activations Density 0.017%

    No Known Activations