© 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. 22-RES-MATRYOSHKA-DC
    7. 1253
    Prev
    Next
    INDEX
    Explanations

    the superlative "most"

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     than
    -1.33
    than
    -1.07
     THAN
    -0.98
     än
    -0.92
    Than
    -0.90
     Than
    -0.82
     niż
    -0.81
     než
    -0.78
     kuin
    -0.78
    THAN
    -0.73
    POSITIVE LOGITS
     simplest
    0.70
     busiest
    0.64
     happiest
    0.63
     saddest
    0.60
     funniest
    0.57
     proudest
    0.57
     coldest
    0.57
    ךְ
    0.57
     visited
    0.56
     photographed
    0.56
    Activations Density 0.115%

    No Known Activations