© 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. 17649
    Prev
    Next
    INDEX
    Explanations

    references to political agendas

    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
    pite
    -0.69
    yste
    -0.68
    yaar
    -0.68
     Neto
    -0.65
     Isolation
    -0.61
     Boyle
    -0.60
    doms
    -0.60
    ťa
    -0.59
    Portály
    -0.59
    TabStop
    -0.59
    POSITIVE LOGITS
     Agenda
    1.81
     agenda
    1.76
    agenda
    1.69
     agendas
    1.65
    Agenda
    1.62
     AGENDA
    1.41
    AGENDA
    1.29
    cheiben
    0.86
     schedule
    0.84
     sched
    0.84
    Activations Density 0.003%

    No Known Activations