© 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. 15374
    Prev
    Next
    INDEX
    Explanations

    references to legal documents and subpoenas

    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
     الحره
    -0.65
    ⓧ
    -0.59
     referenties
    -0.58
    CloseOperation
    -0.56
    chdir
    -0.54
    $​
    -0.54
     Exacts
    -0.54
    UIControlState
    -0.53
    Override
    -0.52
    .*")]
    -0.52
    POSITIVE LOGITS
     subpoena
    1.76
     subpo
    1.46
     Pizarro
    0.79
     summon
    0.77
     summons
    0.77
    Demikian
    0.77
     undangan
    0.72
     Invitation
    0.68
    tvguidetime
    0.68
    azan
    0.67
    Activations Density 0.002%

    No Known Activations