© 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. 93595
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
     réelle
    -0.77
     malades
    -0.58
     scolaires
    -0.55
     dovuto
    -0.55
     refusé
    -0.54
     sacré
    -0.53
     vérit
    -0.53
     tombé
    -0.53
    UNCIL
    -0.52
     Grot
    -0.52
    POSITIVE LOGITS
    دانشنامهٔ
    0.50
    nthetic
    0.50
    хьтан
    0.48
     kasarigan
    0.48
    Filmographie
    0.46
    FunctionFlags
    0.45
    vician
    0.44
     AssemblyCompany
    0.44
    TALL
    0.44
     arm
    0.43
    Activations Density 0.004%

    No Known Activations