© 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. 4884
    Prev
    Next
    INDEX
    Explanations

    to

    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
    AddTagHelper
    -0.93
     MainAxisSize
    -0.90
    CloseOperation
    -0.88
    mybatisplus
    -0.82
     متعلقه
    -0.82
    Portale
    -0.81
    adpleegd
    -0.79
     considérons
    -0.78
    expandindo
    -0.77
     AssemblyTitle
    -0.76
    POSITIVE LOGITS
    ↵
    0.47
    itonitis
    0.45
     x
    0.43
     Ang
    0.42
     Y
    0.42
     X
    0.41
     v
    0.41
     ""))
    0.41
    ionato
    0.40
     pelayanan
    0.40
    Activations Density 0.001%

    No Known Activations