© 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. 26405
    Prev
    Next
    INDEX
    Explanations

    geographic locations and relevant legal terms

    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
    wahati
    -0.76
     Brunei
    -0.73
     Gottfried
    -0.73
    ApiProperty
    -0.68
     Assam
    -0.67
    orable
    -0.66
     prévention
    -0.66
     vectorielles
    -0.66
    orithmic
    -0.65
    Continuity
    -0.65
    POSITIVE LOGITS
     Michigan
    1.65
    Michigan
    1.59
     Detroit
    1.50
    Detroit
    1.45
     MICHIGAN
    1.41
     Mich
    1.28
     Wolver
    1.23
    higan
    1.21
     DETROIT
    1.20
    Mich
    1.17
    Activations Density 0.037%

    No Known Activations