© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6055
    Prev
    Next
    INDEX
    Explanations

    instances of the word "least" or related phrases indicating a minimum requirement or threshold

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     demografica
    -1.09
     مشين
    -0.93
    TemporalType
    -0.82
     CreateTagHelper
    -0.81
     $_"
    -0.80
    ſelf
    -0.80
     دیکھیے
    -0.80
     Theſe
    -0.79
     Wikimedijinoj
    -0.78
    ⋙
    -0.78
    POSITIVE LOGITS
     least
    1.02
     Least
    0.73
    Least
    0.72
    least
    0.69
     LEAST
    0.68
     almeno
    0.67
     минимум
    0.56
    minHeight
    0.53
     zumindest
    0.52
    біль
    0.51
    Activations Density 0.037%

    No Known Activations