© 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. 26392
    Prev
    Next
    INDEX
    Explanations

    words related to data privacy and user information management

    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
    ]")]
    -0.90
     BorderRadius
    -0.86
    EndInit
    -0.85
     CreateTagHelper
    -0.84
    RectangleBorder
    -0.77
     GenerationType
    -0.72
    addContainerGap
    -0.69
    PerformLayout
    -0.68
     الاطلاع
    -0.67
     كومونز
    -0.67
    POSITIVE LOGITS
    lam
    0.52
     partners
    0.48
     faudrait
    0.48
     intptr
    0.48
     faut
    0.47
     suaminya
    0.47
     partner
    0.46
     faudra
    0.46
     livré
    0.45
     Befe
    0.43
    Activations Density 0.015%

    No Known Activations