© 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. 0-CLT-HP
    7. 38326
    Prev
    Next
    INDEX
    Explanations

    size/intensity adjectives

    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
     broad
    -1.19
     mild
    -1.15
    mild
    -0.99
     Mild
    -0.97
    broad
    -0.95
     Broad
    -0.91
    StoryboardSegue
    -0.91
    Broad
    -0.88
     milder
    -0.88
     shallow
    -0.82
    POSITIVE LOGITS
    s
    1.31
    ness
    1.30
    ly
    1.06
    est
    1.04
    ship
    0.88
    scale
    0.85
    nya
    0.82
    shire
    0.78
    nesses
    0.77
    ened
    0.77
    Activations Density 0.119%

    No Known Activations