© 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. 8736
    Prev
    Next
    INDEX
    Explanations

    mentions of different scenarios or scenarios in general

    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
    extAlignment
    -0.86
     bygget
    -0.75
    MessageState
    -0.75
     Sosa
    -0.74
     Mosley
    -0.73
    PMailer
    -0.72
    ostock
    -0.72
     ASE
    -0.71
     Blak
    -0.71
     StatelessWidget
    -0.68
    POSITIVE LOGITS
     scenarios
    1.52
     Scenarios
    1.50
    scenarios
    1.50
     Scenario
    1.47
     scenario
    1.41
    Scenario
    1.30
    scenario
    1.28
    Scen
    1.14
    cenario
    1.09
     Scen
    0.94
    Activations Density 0.003%

    No Known Activations