© 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. 5-CLT-HP
    7. 2575
    Prev
    Next
    INDEX
    Explanations

    position or precedence

    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
     ainfi
    -0.63
     bonté
    -0.57
     eorum
    -0.57
    couvrez
    -0.56
    miyorum
    -0.55
    AndEndTag
    -0.55
     ejus
    -0.55
     fourrure
    -0.54
     épais
    -0.51
     ProtoMessage
    -0.51
    POSITIVE LOGITS
     seat
    0.83
     stage
    0.78
    stage
    0.63
    seat
    0.63
    SceneManagement
    0.52
    CardHeader
    0.51
     ComVisible
    0.50
    XMLSchema
    0.49
     step
    0.48
     grade
    0.48
    Activations Density 0.018%

    No Known Activations