© 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. 30884
    Prev
    Next
    INDEX
    Explanations

    phrases that denote establishment or naming of entities or locations

    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
    ofollow
    -0.60
    UIControlState
    -0.57
     réfugi
    -0.57
     kepem
    -0.56
     allmän
    -0.54
    .
    -0.54
     suivent
    -0.53
     pouvoirs
    -0.51
    WithIOException
    -0.50
     Umum
    -0.50
    POSITIVE LOGITS
     الحره
    0.69
    standers
    0.61
    სქოლიო
    0.60
    FunctionFlags
    0.59
     ब्रेकडाउन
    0.59
     disambiguazione
    0.58
    RoutingModule
    0.58
    Šaltiniai
    0.57
     snippetHide
    0.57
    })*/
    0.57
    Activations Density 0.135%

    No Known Activations