© 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. 0-CLT-HP
    7. 93382
    Prev
    Next
    INDEX
    Explanations

    then

    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
     then
    -1.82
    then
    -1.22
     entonces
    -1.20
     então
    -1.16
    Then
    -1.15
     Then
    -1.11
     THEN
    -1.09
     allora
    -1.01
    THEN
    -0.97
     kemudian
    -0.95
    POSITIVE LOGITS
    WriteAttribute
    0.64
     ordained
    0.57
     baptized
    0.57
    Rüyada
    0.56
     Yahweh
    0.55
     blasphemy
    0.55
     beheaded
    0.55
     industrialized
    0.54
     favorably
    0.54
     demurrer
    0.54
    Activations Density 0.034%

    No Known Activations