© 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. 5042
    Prev
    Next
    INDEX
    Explanations

    biographies

    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
     дописавши
    -0.53
    LookAnd
    -0.51
     oprot
    -0.51
    
    -0.49
    RenderAtEndOf
    -0.49
    AddTagHelper
    -0.49
     فريبيس
    -0.48
    ParallelGroup
    -0.47
    QMetaType
    -0.47
    InjectAttribute
    -0.46
    POSITIVE LOGITS
    près
    0.54
    setLayoutManager
    0.53
    Filmographie
    0.50
    Assemblée
    0.50
    SBATCH
    0.49
     Watertown
    0.47
    UMNS
    0.46
     lactic
    0.46
    WASH
    0.46
     ApJ
    0.46
    Activations Density 0.013%

    No Known Activations