© 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. 22-RES-MATRYOSHKA-DC
    7. 2909
    Prev
    Next
    INDEX
    Explanations

    language related to discovering human remains after death

    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.22.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.22.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
    MigrationBuilder
    -0.69
    adaptiveStyles
    -0.65
    awtextra
    -0.56
     BoxDecoration
    -0.55
     /\.(
    -0.54
    celes
    -0.54
    mobileqq
    -0.53
    ftagPool
    -0.52
    fromnode
    -0.50
    Portail
    -0.50
    POSITIVE LOGITS
     wreckage
    1.23
     carcasses
    1.20
     carcass
    1.19
     bodies
    1.18
     remains
    1.15
     corpses
    1.13
     mangled
    1.13
     corpse
    1.08
    remains
    1.05
     charred
    1.05
    Activations Density 0.461%

    No Known Activations