© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9694
    Prev
    Next
    INDEX
    Explanations

    references to U.S. political figures and legislative activities

    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
    (;;)
    -0.54
    AdapterFactory
    -0.48
    #+#
    -0.48
     BoxFit
    -0.47
    WaitGroup
    -0.47
     crowds
    -0.46
     juger
    -0.46
    balleur
    -0.45
     dimenti
    -0.44
     testSet
    -0.43
    POSITIVE LOGITS
     متعلقه
    0.73
     كومونز
    0.67
    setupUi
    0.65
     senator
    0.63
     lawmaker
    0.63
     Senator
    0.62
     beginnetje
    0.62
    casio
    0.61
    MigrationBuilder
    0.61
    Senator
    0.60
    Activations Density 0.116%

    No Known Activations