© 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. 25605
    Prev
    Next
    INDEX
    Explanations

    discussions related to political dissent and human rights issues

    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
    OGND
    -0.65
    rrggbb
    -0.64
    IsContent
    -0.52
     Spisak
    -0.52
    cordova
    -0.52
    isOk
    -0.51
    مزید
    -0.50
     rosario
    -0.50
     skim
    -0.46
     noDo
    -0.46
    POSITIVE LOGITS
     виправивши
    0.72
     dared
    0.57
    Tikang
    0.55
     dares
    0.55
     DISE
    0.52
     courage
    0.51
     Dare
    0.51
    ragos
    0.50
     disobedience
    0.50
    jsonwebtoken
    0.49
    Activations Density 0.144%

    No Known Activations