© 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. 3305
    Prev
    Next
    INDEX
    Explanations

    mentions of political situations and instances of suffering related to governance

    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
    จึง
    -0.82
    therefore
    -0.73
    MigrationBuilder
    -0.71
     therefore
    -0.69
    thus
    -0.68
    SequentialGroup
    -0.68
     الحره
    -0.67
     därför
    -0.67
    ungkinkan
    -0.65
    เลย
    -0.64
    POSITIVE LOGITS
     nonetheless
    0.77
     trotzdem
    0.70
    それでも
    0.66
     nevertheless
    0.63
    それにしても
    0.58
     dennoch
    0.57
     still
    0.56
    卻
    0.54
    却
    0.51
    却是
    0.49
    Activations Density 1.386%

    No Known Activations