© 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. 9842
    Prev
    Next
    INDEX
    Explanations

    references to urgency or speed, particularly related to the term "rush"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    发表于
    -0.99
     Parcelable
    -0.91
     palvel
    -0.90
     Miquel
    -0.88
    زب
    -0.88
    hubanes
    -0.88
     greateſt
    -0.87
     NSCoder
    -0.87
    contentLoaded
    -0.86
    #+#
    -0.86
    POSITIVE LOGITS
     Rush
    1.51
    Rush
    1.38
    rus
    1.27
     rush
    1.22
     RUSH
    1.22
    rush
    1.20
     Rus
    1.16
     Russell
    1.04
     RUS
    0.96
     rushes
    0.95
    Activations Density 0.010%

    No Known Activations