© 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. 4-CLT-HP
    7. 1145
    Prev
    Next
    INDEX
    Explanations

    words ending in "ly"

    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
    IntoConstraints
    -0.63
     ComVisible
    -0.61
    Erreferentziak
    -0.56
     dormitorios
    -0.56
    TextWatcher
    -0.56
    Rè
    -0.56
    flexGrow
    -0.54
    Collegamenti
    -0.53
    esModule
    -0.52
     mû
    -0.52
    POSITIVE LOGITS
     enough
    0.87
     like
    0.76
     similar
    0.76
     the
    0.69
     not
    0.69
     without
    0.64
    similar
    0.62
     both
    0.57
     lacking
    0.55
    enough
    0.54
    Activations Density 0.004%

    No Known Activations