© 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. 92607
    Prev
    Next
    INDEX
    Explanations

    introductions

    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
    ValueGenerated
    -0.57
    uthor
    -0.57
    EClass
    -0.53
    bootstrapcdn
    -0.53
    XMLSchema
    -0.52
    цездатний
    -0.52
    MigrationBuilder
    -0.50
    Rüyada
    -0.50
    kits
    -0.50
    ंगे
    -0.49
    POSITIVE LOGITS
    RegistryLite
    0.51
    參見
    0.49
     reasons
    0.49
    XmlAccessorType
    0.46
     lucky
    0.46
    TargetException
    0.46
     BioLib
    0.45
     indépendant
    0.45
    UrlResolution
    0.45
    GIH
    0.45
    Activations Density 0.002%

    No Known Activations