© 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. 93355
    Prev
    Next
    INDEX
    Explanations

    composition

    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
     composition
    -1.43
     Composition
    -1.20
    composition
    -1.12
    ton
    -1.08
     COMPOSITION
    -1.04
     culture
    -1.01
    Composition
    -0.94
    TON
    -0.86
    COMPOSITION
    -0.82
     composición
    -0.80
    POSITIVE LOGITS
    ally
    0.54
    al
    0.53
     jugado
    0.46
    alnya
    0.46
    gså
    0.46
    brać
    0.46
    ंदीखरीदारी
    0.45
    ial
    0.45
    ality
    0.44
    faktor
    0.44
    Activations Density 0.705%

    No Known Activations