© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94768
    Prev
    Next
    INDEX
    Explanations

    to

    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
     تضيفلها
    -0.74
     وتسجيلات
    -0.70
     <=",
    -0.70
     itſelf
    -0.69
    الدراسه
    -0.65
    umą
    -0.63
     grève
    -0.62
     '{@
    -0.60
    rmtree
    -0.60
     vectorielles
    -0.59
    POSITIVE LOGITS
     that
    0.55
     all
    0.49
     this
    0.47
     AppCompat
    0.46
     us
    0.43
    PageContext
    0.43
     autos
    0.43
     how
    0.42
     osmosis
    0.42
     gelegen
    0.42
    Activations Density 0.002%

    No Known Activations