© 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. 200
    Prev
    Next
    INDEX
    Explanations

    words ending in "est" or related superlative adjectives

    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
    Mucha
    -0.66
     Many
    -0.62
    many
    -0.62
    twimg
    -0.57
     esternos
    -0.57
     many
    -0.56
    Many
    -0.55
    Various
    -0.55
     Several
    -0.55
    rzez
    -0.55
    POSITIVE LOGITS
     best
    1.95
     strongest
    1.95
     highest
    1.94
     greatest
    1.93
     healthiest
    1.90
     longest
    1.88
     largest
    1.86
    highest
    1.85
    greatest
    1.84
     safest
    1.82
    Activations Density 0.784%

    No Known Activations