© 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. 4-CLT-HP
    7. 1332
    Prev
    Next
    INDEX
    Explanations

    for

    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
    Према
    -0.62
     wireType
    -0.62
    delà
    -0.60
    WebElementEntity
    -0.57
    dientemente
    -0.56
    RunAsync
    -0.55
    CompleteListener
    -0.55
    ErrUnexpectedEOF
    -0.55
     compac
    -0.53
     SIAM
    -0.52
    POSITIVE LOGITS
     reputable
    0.65
     tips
    0.63
     local
    0.59
     Mark
    0.58
     companies
    0.57
     places
    0.57
    getInputStream
    0.52
     expert
    0.51
     websites
    0.51
     sites
    0.50
    Activations Density 0.003%

    No Known Activations