© 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. 597
    Prev
    Next
    INDEX
    Explanations

    webpage text snippets

    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
     equally
    -0.54
     draught
    -0.53
     similarly
    -0.46
     Pharisees
    -0.44
    DockStyle
    -0.44
     pretreatment
    -0.43
    べた
    -0.42
     Nesse
    -0.42
    unite
    -0.42
    Subjects
    -0.42
    POSITIVE LOGITS
    randrange
    0.59
     tromper
    0.58
    Referencie
    0.56
    CodeAnalysis
    0.54
     nôtre
    0.54
    大家好
    0.54
     <",
    0.51
    illem
    0.50
    GraphicsUnit
    0.49
     courants
    0.49
    Activations Density 0.040%

    No Known Activations