© 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. 3441
    Prev
    Next
    INDEX
    Explanations

    NASA

    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
     der
    -0.44
     dach
    -0.42
     gim
    -0.42
    체
    -0.41
     zaz
    -0.41
     activities
    -0.40
     lược
    -0.40
     boats
    -0.40
    TZ
    -0.39
     evaluations
    -0.39
    POSITIVE LOGITS
    Демографія
    0.90
     snippetHide
    0.77
     GenerationType
    0.75
    Enllaces
    0.70
    featureID
    0.68
    berdayakan
    0.67
     IBOutlet
    0.67
    новништво
    0.65
     rigue
    0.64
     wikipagina
    0.63
    Activations Density 0.001%

    No Known Activations