© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10495
    Prev
    Next
    INDEX
    Explanations

    themes related to existential threats and the survival of humanity

    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
    Negative Logits
     residual
    -0.53
     AssemblyProduct
    -0.50
     patterns
    -0.49
     članak
    -0.49
    Symptom
    -0.48
     Patterns
    -0.48
    Complexity
    -0.47
    큼
    -0.47
    Lé
    -0.46
     Dez
    -0.46
    POSITIVE LOGITS
     survival
    0.90
     survie
    0.84
    survival
    0.81
     Survival
    0.79
     MainAxisSize
    0.78
    Survival
    0.73
     soprav
    0.71
     viability
    0.70
     survive
    0.67
     supervivencia
    0.67
    Activations Density 0.146%

    No Known Activations