© 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. 94097
    Prev
    Next
    INDEX
    Explanations

    superlatives and adverbs

    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
     next
    -1.25
    next
    -1.09
    Next
    -0.94
     prochaine
    -0.91
     prossima
    -0.89
     nächste
    -0.88
     nästa
    -0.82
     exactly
    -0.80
     næste
    -0.78
    His
    -0.76
    POSITIVE LOGITS
    帖最后由
    0.72
    )':
    0.66
    ConstraintMaker
    0.66
    RenderAtEndOf
    0.65
    XmlEnum
    0.64
     متعلقه
    0.64
    EDEFAULT
    0.63
    ugges
    0.63
    contentLoaded
    0.62
    iné
    0.61
    Activations Density 1.907%

    No Known Activations