© 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. 14760
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shower" 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
    Not in Any Lists

    No Comments

    Negative Logits
     Ej
    -0.77
     Litt
    -0.71
     않
    -0.67
     JpaRepository
    -0.66
    invokeLater
    -0.64
     lục
    -0.64
    canActivate
    -0.63
    acas
    -0.63
    Palindrome
    -0.63
     Abp
    -0.62
    POSITIVE LOGITS
     shower
    1.73
     Shower
    1.66
    Shower
    1.60
    shower
    1.52
     showers
    1.38
     Showers
    1.33
     showering
    1.27
     Dusche
    1.13
     showered
    1.08
     doccia
    1.05
    Activations Density 0.002%

    No Known Activations