© 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. 28464
    Prev
    Next
    INDEX
    Explanations

    terms related to disturbances and disruptions in systems or 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
    مكان
    -0.65
    Mes
    -0.63
    VITA
    -0.62
     للاسماء
    -0.60
     Lowe
    -0.59
    ForValue
    -0.59
    XL
    -0.59
    роят
    -0.59
    option
    -0.59
    belo
    -0.59
    POSITIVE LOGITS
     disruptions
    1.23
     disturbances
    1.20
     Disturb
    1.20
     disrupt
    1.18
     disruption
    1.16
     disturbance
    1.14
    urbing
    1.13
     disrupted
    1.09
    urbed
    1.04
     disturbed
    1.03
    Activations Density 0.029%

    No Known Activations