© 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. 12467
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "ES" and its variations, which likely indicates an error or status related to system processes

    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
     Wallflower
    -0.79
     bianchi
    -0.73
    BoxShadow
    -0.73
     ago
    -0.71
     Brown
    -0.69
     đương
    -0.69
     Cabinet
    -0.68
     Высо
    -0.68
    LikeLike
    -0.66
    djangoproject
    -0.66
    POSITIVE LOGITS
     ES
    1.45
     Estelle
    1.20
     Esch
    1.15
    ES
    1.13
     Es
    1.02
     Esau
    0.99
     ESC
    0.98
    elasticsearch
    0.96
     Esquire
    0.95
    Esther
    0.94
    Activations Density 0.040%

    No Known Activations