© 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. 5352
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     通販
    -0.57
     vastaan
    -0.54
    Personensuche
    -0.47
    "],
    -0.44
    bodyParser
    -0.44
    horabuena
    -0.42
    devamını
    -0.42
    AccessorTable
    -0.42
     Synonyms
    -0.41
     fondo
    -0.41
    POSITIVE LOGITS
     &___
    0.65
     was
    0.64
     could
    0.64
    AndEndTag
    0.63
     للمعارف
    0.63
    MemoryWarning
    0.61
     ***!
    0.57
    httphttps
    0.56
     employs
    0.56
     showed
    0.55
    Activations Density 0.001%

    No Known Activations