© 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. 91293
    Prev
    Next
    INDEX
    Explanations

    science and technology

    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
    CompleteListener
    -0.64
    awaiter
    -0.62
    expandindo
    -0.60
    UrlResolution
    -0.54
    apimachinery
    -0.52
     समीक्षाओं
    -0.52
     CreateTagHelper
    -0.50
     stanovnika
    -0.50
     WQS
    -0.49
    zzleHttp
    -0.49
    POSITIVE LOGITS
    encanaan
    0.65
     faibles
    0.57
     Thin
    0.57
     unités
    0.56
    Thin
    0.56
    arrête
    0.56
    vägen
    0.56
    latt
    0.54
     malha
    0.54
     précie
    0.53
    Activations Density 0.010%

    No Known Activations