© 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. 24-RES-MATRYOSHKA-DC
    7. 1606
    Prev
    Next
    INDEX
    Explanations

    sequences of words describing cleaning or paper products

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     متعلقه
    -0.60
    ArgsConstructor
    -0.50
    #
    -0.49
    pushFollow
    -0.49
    LayoutConstraint
    -0.49
    '][]
    -0.48
     UIFont
    -0.48
     pilotes
    -0.47
    UIFont
    -0.47
     harganya
    -0.47
    POSITIVE LOGITS
     cleaning
    1.66
     clean
    1.48
     Cleaning
    1.45
     cleans
    1.40
     cleaned
    1.39
    Cleaning
    1.39
    Clean
    1.38
     Clean
    1.37
     cleanliness
    1.36
    clean
    1.35
    Activations Density 1.263%

    No Known Activations