© 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. 1-CLT-HP
    7. 15603
    Prev
    Next
    INDEX
    Explanations

    polishing, deoxy, or "Pea"

    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
    Pea
    -0.88
     Pea
    -0.84
    pea
    -0.68
     pea
    -0.66
    ]")]
    -0.64
     AssemblyCompany
    -0.63
    "}")
    -0.62
     Pease
    -0.62
    发表于
    -0.60
    awtextra
    -0.60
    POSITIVE LOGITS
     Vordergrund
    0.47
    ībā
    0.46
    bí
    0.46
     Map
    0.46
     LEC
    0.46
    ungkinkan
    0.44
     épis
    0.44
    hib
    0.44
    ComponentName
    0.44
    adaan
    0.44
    Activations Density 0.007%

    No Known Activations