© 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. 24-RES-MATRYOSHKA-DC
    7. 565
    Prev
    Next
    INDEX
    Explanations

    negative sentiment about the Affordable Care Act (Obamacare).

    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
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.84
    存于互联网档案馆
    -0.71
    脚注の使い方
    -0.68
     ivelany
    -0.68
    ScopeManager
    -0.61
    httphttps
    -0.58
    arXiv
    -0.57
     curfew
    -0.55
    ArgsConstructor
    -0.54
     Theatres
    -0.54
    POSITIVE LOGITS
     coverage
    1.24
     Coverage
    1.13
    Coverage
    1.05
     insurance
    1.05
    coverage
    1.05
     COVERAGE
    0.93
    insurance
    0.91
     insured
    0.91
     cobertura
    0.90
     uninsured
    0.90
    Activations Density 0.296%

    No Known Activations