© 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. 42166
    Prev
    Next
    INDEX
    Explanations

    past participles used adjectivally

    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
     Majefty
    -0.98
     Efq
    -0.90
    ſelf
    -0.88
     '\\;'
    -0.85
     myſelf
    -0.85
     whoſe
    -0.83
     becauſe
    -0.80
     uſ
    -0.80
     Jefus
    -0.80
    setVerticalGroup
    -0.79
    POSITIVE LOGITS
     rowspan
    0.35
    ंबर
    0.34
    ýchod
    0.34
     aleación
    0.34
     actionMode
    0.33
     rette
    0.33
     ‘
    0.32
     \
    0.31
    ™
    0.31
    슷
    0.31
    Activations Density 0.053%

    No Known Activations