© 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. 24-RES-MATRYOSHKA-DC
    7. 1493
    Prev
    Next
    INDEX
    Explanations

    political scandals and corruption, especially in Brazil

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     ‚
    -0.65
     recognisable
    -0.64
     nicely
    -0.63
     Organisations
    -0.62
     localisation
    -0.60
     colourful
    -0.60
     utilising
    -0.60
     rumoured
    -0.60
     costes
    -0.59
     utilise
    -0.58
    POSITIVE LOGITS
     XNUMX
    0.69
     analyzes
    0.65
     contemplates
    0.64
    ºC
    0.63
     permanence
    0.63
    º
    0.60
     anguish
    0.59
    aneity
    0.58
    itism
    0.56
     bibliographic
    0.55
    Activations Density 0.996%

    No Known Activations