© 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. 21012
    Prev
    Next
    INDEX
    Explanations

    references to sanctions and their implications in relation to Russia

    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
    AutoField
    -0.50
    lji
    -0.47
     protects
    -0.47
     sujets
    -0.47
    estine
    -0.46
    SequentialGroup
    -0.46
    Cerv
    -0.45
    🏼
    -0.45
     Carroll
    -0.45
     unknownFields
    -0.45
    POSITIVE LOGITS
     Sanctions
    1.12
     sanctions
    1.05
    ########.
    0.90
    脚注の使い方
    0.81
     boycott
    0.79
     Efq
    0.79
    InitVars
    0.77
    elemField
    0.76
     ModelExpression
    0.75
     незавершена
    0.75
    Activations Density 0.014%

    No Known Activations