© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2524
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    IContainer
    -0.68
    脚注の使い方
    -0.66
     initComponents
    -0.59
    ᅠ
    -0.59
     gainera
    -0.58
    rungsseite
    -0.58
    dried
    -0.55
     myö
    -0.54
     Dried
    -0.52
    Muff
    -0.51
    POSITIVE LOGITS
     being
    0.71
    évaluateur
    0.68
     winning
    0.60
    MemoryWarning
    0.60
     successfully
    0.60
    ::::::::
    0.58
    Diweddarwch
    0.56
     his
    0.56
     AssemblyProduct
    0.54
     helping
    0.53
    Activations Density 0.005%

    No Known Activations