© 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. 23123
    Prev
    Next
    INDEX
    Explanations

    context related to survival and hardship during difficult circumstances

    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
     khas
    -0.52
     חיצוניים
    -0.52
     sign
    -0.51
    essa
    -0.49
     leading
    -0.47
    WithIOException
    -0.45
     esquina
    -0.45
    SaveChangesAsync
    -0.45
    ,‎
    -0.45
     turno
    -0.45
    POSITIVE LOGITS
     Penh
    0.66
    bootstrapcdn
    0.62
    Datuak
    0.61
    ArrowToggle
    0.60
    paksa
    0.59
    esModule
    0.58
     peor
    0.57
     subsistence
    0.57
     shotguns
    0.57
    Portail
    0.56
    Activations Density 0.136%

    No Known Activations