© 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. 5-CLT-HP
    7. 92898
    Prev
    Next
    INDEX
    Explanations

    your

    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
     Nitrate
    -0.46
     didel
    -0.46
    amaño
    -0.45
     Fossil
    -0.44
     phylogeny
    -0.44
     nebula
    -0.43
     Hidden
    -0.43
     vegano
    -0.43
     ordnance
    -0.41
     tomography
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    1.00
    GraphicsUnit
    0.96
     EconPapers
    0.90
    fjspx
    0.82
    ThroughAttribute
    0.81
     InputDecoration
    0.78
     resourceCulture
    0.77
     فريبيس
    0.75
    fortawesome
    0.73
    TagMode
    0.73
    Activations Density 0.000%

    No Known Activations