© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13292
    Prev
    Next
    INDEX
    Explanations

    the, a

    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
     المعيارى
    -0.88
     bezeichneter
    -0.74
     nakalista
    -0.68
     дописавши
    -0.67
     insuffisamment
    -0.66
    曖昧さ回避
    -0.66
    AndEndTag
    -0.65
    ChildScrollView
    -0.65
    $_['
    -0.64
    AccessorTable
    -0.63
    POSITIVE LOGITS
     moulin
    0.57
    entration
    0.54
     roar
    0.54
    ılığı
    0.53
     contingent
    0.52
    我會
    0.51
     proud
    0.50
     personally
    0.50
     Bering
    0.50
     Vasco
    0.50
    Activations Density 0.011%

    No Known Activations