© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 461
    Prev
    Next
    INDEX
    Explanations

    words related to political and social issues and trends

    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.22.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.22.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
    onViewCreated
    -0.71
     avoient
    -0.66
     poffe
    -0.65
     feroit
    -0.65
     Contribute
    -0.62
     Monfieur
    -0.61
     zorgt
    -0.59
     käns
    -0.59
     ErrInvalid
    -0.59
     confers
    -0.59
    POSITIVE LOGITS
     slowly
    1.13
     gradually
    1.08
     dwind
    1.07
     become
    1.00
     becomes
    0.93
    slowly
    0.90
     begin
    0.88
     suddenly
    0.86
     grow
    0.86
    Slowly
    0.86
    Activations Density 3.350%

    No Known Activations