© 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. 21035
    Prev
    Next
    INDEX
    Explanations

    the term "strict" and its variations, indicating a focus on strictness or rigidity in various contexts

    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
    ReusableCell
    -0.81
    Aver
    -0.77
    padu
    -0.74
     bary
    -0.73
     AppBundle
    -0.73
    ValueStyle
    -0.73
    соль
    -0.73
     Beren
    -0.72
    Marlene
    -0.72
     brooch
    -0.72
    POSITIVE LOGITS
     strict
    1.16
    strict
    1.14
     strictly
    1.07
    Strict
    1.05
     Strict
    1.03
    Strictly
    0.95
    STRICT
    0.94
     Strictly
    0.93
    严格
    0.87
     strictest
    0.84
    Activations Density 0.007%

    No Known Activations