© 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. 32135
    Prev
    Next
    INDEX
    Explanations

    specific legal terms or citations related to immigration and court proceedings

    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
     itſelf
    -0.63
    aulted
    -0.57
    tonode
    -0.57
     reproach
    -0.57
    olescence
    -0.57
    步
    -0.56
    UNTAS
    -0.53
     Fries
    -0.53
    edly
    -0.53
     Amiens
    -0.53
    POSITIVE LOGITS
     estekak
    0.69
     متعلقه
    0.66
     tartalomajánló
    0.65
     للاسماء
    0.64
    parsedMessage
    0.59
     للمعارف
    0.57
    InvalidProtocol
    0.57
     يتيمه
    0.57
    ulkan
    0.56
    ьаж
    0.56
    Activations Density 0.032%

    No Known Activations