© 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. 8801
    Prev
    Next
    INDEX
    Explanations

    references to splits and divisions within organizations or groups

    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
    +#+#
    -0.69
     HasFactory
    -0.65
    stateProvider
    -0.62
    ArgumentParser
    -0.62
    awtextra
    -0.61
    AnchorTagHelper
    -0.59
    virons
    -0.57
    ishe
    -0.57
    asable
    -0.56
    VIRONMENT
    -0.55
    POSITIVE LOGITS
     estekak
    0.73
     متعلقه
    0.60
    
    0.57
     utafitiHapana
    0.52
     فريبيس
    0.51
    ValueStyle
    0.49
    Jeografia
    0.48
    GEBURTSDATUM
    0.47
     صوتيه
    0.45
     Hatt
    0.45
    Activations Density 0.351%

    No Known Activations