© 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. 92616
    Prev
    Next
    INDEX
    Explanations

    description, argumentation, analysis

    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
     their
    -0.66
     NgModule
    -0.65
    BeginContext
    -0.63
    FTFY
    -0.62
    complexType
    -0.61
    GEBURTSDATUM
    -0.60
    webElementXpaths
    -0.58
    sizeCache
    -0.58
    
    -0.55
    enumi
    -0.54
    POSITIVE LOGITS
     as
    0.89
     held
    0.79
     sebagai
    0.66
     belong
    0.65
     drawn
    0.62
     HELD
    0.61
     belonged
    0.61
     involved
    0.60
     backed
    0.60
     antaranya
    0.60
    Activations Density 0.004%

    No Known Activations