© 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. 18815
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce discussions or assessments, particularly in legal or procedural 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
    Negative Logits
     detail
    -0.74
     details
    -0.74
     Details
    -0.66
    Details
    -0.65
    details
    -0.60
     DETAILS
    -0.58
    详情
    -0.58
    detail
    -0.57
    czegóły
    -0.57
     détails
    -0.56
    POSITIVE LOGITS
    AnimationsModule
    0.72
    TagMode
    0.69
     pulumi
    0.68
     useAppContext
    0.68
    StoryboardSegue
    0.68
    msgTypes
    0.66
    DrawerToggle
    0.66
     createSprite
    0.65
    ScopeManager
    0.63
    PyExc
    0.63
    Activations Density 0.023%

    No Known Activations