© 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. 30814
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or entity tied to activities or experiences

    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
     Wheeler
    -0.71
     Redding
    -0.69
    etton
    -0.68
     dislocations
    -0.65
    son
    -0.65
     Hartley
    -0.64
     gr
    -0.64
    uscht
    -0.63
    dys
    -0.63
    uscular
    -0.63
    POSITIVE LOGITS
    Ba
    1.28
     BA
    1.28
     Ba
    1.26
     Baumann
    1.15
     Baal
    1.13
     Baf
    1.11
     Baer
    1.09
    BA
    1.06
     ba
    1.03
    Bailey
    1.03
    Activations Density 0.041%

    No Known Activations