© 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. 31802
    Prev
    Next
    INDEX
    Explanations

    references to populated places and communities, particularly in terms of their classification and administrative status

    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
    RAH
    -0.63
    rah
    -0.50
     distanciation
    -0.48
     profession
    -0.47
     identifiable
    -0.47
     Selbst
    -0.47
     Laurence
    -0.46
    sum
    -0.46
    Sco
    -0.45
     médi
    -0.45
    POSITIVE LOGITS
     Roskov
    0.74
    Билгалдахарш
    0.71
    PreferredItem
    0.71
    BeginInit
    0.67
    AsUp
    0.67
    Contours
    0.67
     Administrativna
    0.66
     ویکی‌پدیا
    0.65
    AddTagHelper
    0.64
    RUnlock
    0.64
    Activations Density 0.007%

    No Known Activations