© 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. 24412
    Prev
    Next
    INDEX
    Explanations

    statements indicating ongoing or significant conditions and their implications

    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
     there
    -0.68
     few
    -0.67
     are
    -0.66
     two
    -0.66
     several
    -0.64
     numerous
    -0.63
     many
    -0.63
     
    -0.63
    erp
    -0.59
     buenos
    -0.58
    POSITIVE LOGITS
    Adolf
    0.71
     pouvoirs
    0.70
    EndGlobal
    0.70
     weevil
    0.70
    complexContent
    0.68
     lordship
    0.67
     useRouter
    0.67
     gluon
    0.67
    
    0.67
     pulpit
    0.66
    Activations Density 0.048%

    No Known Activations