© 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. 10563
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and notable landmarks

    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
    Santis
    -0.75
     Tad
    -0.68
    Björn
    -0.66
     Björn
    -0.66
    Abitanti
    -0.65
    ILayout
    -0.63
    Tad
    -0.60
    rupal
    -0.60
    لينكات
    -0.59
     Hag
    -0.59
    POSITIVE LOGITS
     Pittsburgh
    1.22
    Pittsburgh
    1.16
     Jharkhand
    1.05
     Steelers
    1.02
    Pitt
    0.84
     Pitt
    0.84
     Allegheny
    0.79
     Ruhr
    0.78
     Youngstown
    0.77
     PBT
    0.76
    Activations Density 0.132%

    No Known Activations