© 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. 9525
    Prev
    Next
    INDEX
    Explanations

    terms related to the revocation of parole or legal 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
     Waray
    -0.72
    RectangleBorder
    -0.61
    InputTagHelper
    -0.57
     sca
    -0.56
     Ili
    -0.56
    ly
    -0.54
     ensi
    -0.54
     Réponses
    -0.54
     BorderLayout
    -0.54
    Bibliograf
    -0.54
    POSITIVE LOGITS
     revocation
    1.00
     revoke
    0.98
     revoked
    0.93
    RegistryLite
    0.86
    ⓧ
    0.81
    voke
    0.73
    vocable
    0.69
     Félix
    0.65
    Становништво
    0.65
     Roch
    0.62
    Activations Density 0.002%

    No Known Activations