© 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. 18-RES-MATRYOSHKA-DC
    7. 1256
    Prev
    Next
    INDEX
    Explanations

    words related to a crime scene with a focus on the bathtub and water around the victim and in the surrounding rooms and dates of the crime.

    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.18.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.18.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
     Viator
    -0.55
     stadiums
    -0.55
     cherchés
    -0.54
     convoy
    -0.53
    Personensuche
    -0.49
     ویکی‌پدیا
    -0.48
     corte
    -0.47
    haden
    -0.47
     asfalto
    -0.47
    buttonText
    -0.47
    POSITIVE LOGITS
     room
    1.33
     bedroom
    1.27
     rooms
    1.22
     Room
    1.19
     bedrooms
    1.16
     kitchen
    1.15
     ceiling
    1.14
     floor
    1.12
     ROOM
    1.11
     Bedroom
    1.09
    Activations Density 1.178%

    No Known Activations