© 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. 14194
    Prev
    Next
    INDEX
    Explanations

    solution

    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
     Solution
    -0.69
     solution
    -0.68
     solutions
    -0.64
     SOLUTION
    -0.63
    solution
    -0.63
     CreateTagHelper
    -0.60
    Solution
    -0.59
     Solutions
    -0.55
    Solutions
    -0.53
    AddField
    -0.53
    POSITIVE LOGITS
     protoimpl
    0.66
    ekyll
    0.62
    RuleContext
    0.59
    Доброго
    0.57
     userSchema
    0.56
    QName
    0.54
    WireFormatLite
    0.54
    queryInterface
    0.53
     readline
    0.52
     GeV
    0.51
    Activations Density 0.056%

    No Known Activations