© 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. 11849
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "U.S." or contexts referring to the United States

    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
    TypedDataSet
    -0.71
     
    -0.65
     فريبيس
    -0.59
    VERSION
    -0.57
     pot
    -0.55
    aima
    -0.54
     ses
    -0.51
    BackStack
    -0.51
     المعيارى
    -0.51
     abord
    -0.50
    POSITIVE LOGITS
    ſelf
    1.20
     raiſ
    1.08
     Theſe
    1.05
     himſelf
    1.05
     Efq
    1.01
    ſelves
    0.97
     Anſ
    0.96
     purpoſe
    0.95
     Beſ
    0.94
    findpost
    0.94
    Activations Density 0.079%

    No Known Activations