© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42721
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in -ive

    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
    rungsseite
    -1.04
    GEBURTSDATUM
    -0.98
    ing
    -0.93
    ative
    -0.92
    تقاوى
    -0.84
    !*\
    -0.84
    OGND
    -0.82
     مرئيه
    -0.79
    NameInMap
    -0.76
    expandindo
    -0.76
    POSITIVE LOGITS
     capacity
    0.49
     Capacity
    0.44
     change
    0.44
     approach
    0.43
     capo
    0.42
     SIAM
    0.42
    ientôt
    0.41
    equality
    0.41
     framework
    0.40
     annotations
    0.40
    Activations Density 0.172%

    No Known Activations