© 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. 5971
    Prev
    Next
    INDEX
    Explanations

    references to political scandals and corruption

    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
    
    -1.01
     Réponses
    -0.92
    NUMX
    -0.79
    SourceChecksum
    -0.77
    !*\
    -0.76
     />";
    -0.75
     Numerade
    -0.74
    \"></
    -0.72
     beginnetje
    -0.71
    setupUi
    -0.71
    POSITIVE LOGITS
     allegations
    0.82
     allegation
    0.74
     revelations
    0.69
     scandals
    0.69
     scandal
    0.68
     accusations
    0.64
    Alleg
    0.62
     allege
    0.57
     accusation
    0.57
     corruption
    0.56
    Activations Density 0.688%

    No Known Activations