© 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. 86
    Prev
    Next
    INDEX
    Explanations

    Prepositions and time-related words

    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
    until
    -0.54
     until
    -0.47
     particulière
    -0.45
    adding
    -0.44
     autres
    -0.43
    Until
    -0.42
     leden
    -0.41
    while
    -0.41
    winning
    -0.40
     Until
    -0.39
    POSITIVE LOGITS
     esternos
    0.92
    StoryboardSegue
    0.91
     يتيمه
    0.90
     صوتيه
    0.87
     myſelf
    0.85
     Reſ
    0.79
     Anſ
    0.76
    UnsafeEnabled
    0.75
    Personensuche
    0.75
    twimg
    0.73
    Activations Density 0.007%

    No Known Activations