© 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. 6-RES-MATRYOSHKA-DC
    7. 412
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives and phrases

    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
    ResumeLayout
    -0.75
     poco
    -0.66
     Very
    -0.64
     nice
    -0.63
    ViewFeatures
    -0.62
    很
    -0.61
     Much
    -0.60
    very
    -0.60
    er
    -0.59
    rzez
    -0.59
    POSITIVE LOGITS
    most
    1.49
     healthiest
    1.49
     best
    1.48
     greatest
    1.47
     freshest
    1.45
     strongest
    1.45
     safest
    1.45
     happiest
    1.45
     heaviest
    1.42
     most
    1.41
    Activations Density 1.204%

    No Known Activations