© 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. 25321
    Prev
    Next
    INDEX
    Explanations

    terms related to warranty or liability disclaimers

    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
    noons
    -0.49
    pexpr
    -0.49
    зулта
    -0.48
    _
    -0.48
    🏻‍♀️
    -0.48
    FetchType
    -0.47
     مشين
    -0.46
    expandindo
    -0.46
    gameserver
    -0.46
    utnant
    -0.45
    POSITIVE LOGITS
     WARRANTY
    2.53
     warranty
    1.52
     Warranty
    1.50
    WARRANTY
    1.26
    Warranty
    1.25
    warranty
    1.25
     GARANT
    0.85
     warranties
    0.81
     warran
    0.68
     Garantie
    0.67
    Activations Density 0.000%

    No Known Activations