© 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. 3-RES-MATRYOSHKA-DC
    7. 1301
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating comparison

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     great
    -0.83
     very
    -0.80
     high
    -0.80
    great
    -0.73
     Low
    -0.71
    very
    -0.70
     High
    -0.69
     low
    -0.69
     highly
    -0.68
     Very
    -0.68
    POSITIVE LOGITS
     thicker
    1.66
    Larger
    1.64
     stronger
    1.63
    higher
    1.63
     thinner
    1.63
     bigger
    1.63
    Smaller
    1.61
    larger
    1.60
    bigger
    1.59
     narrower
    1.59
    Activations Density 0.518%

    No Known Activations