© 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. 18-RES-MATRYOSHKA-DC
    7. 1367
    Prev
    Next
    INDEX
    Explanations

    legal opinions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    stateMutability
    -0.60
    posedge
    -0.54
    Passe
    -0.45
     rétro
    -0.44
    cheek
    -0.43
    Спо
    -0.40
    Condol
    -0.40
    paku
    -0.40
    érieure
    -0.40
    appé
    -0.40
    POSITIVE LOGITS
     jury
    1.62
     juries
    1.49
     jurors
    1.45
     trial
    1.41
     Trial
    1.29
    jury
    1.29
    trial
    1.27
    Jury
    1.27
    Trial
    1.26
     Jury
    1.26
    Activations Density 1.230%

    No Known Activations