© 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. 15288
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of warranty or guarantee

    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
     warranty
    -0.88
    warranty
    -0.85
    WARRANTY
    -0.84
     Warranty
    -0.83
     WARRANTY
    -0.82
    Warranty
    -0.74
    InputBorder
    -0.61
     oaths
    -0.60
     GARANT
    -0.60
    multer
    -0.57
    POSITIVE LOGITS
    
    0.73
    υτό
    0.57
     incess
    0.52
    jména
    0.51
    市镇
    0.50
     Diakses
    0.49
     lẽ
    0.49
     davran
    0.49
    QMetaType
    0.48
    wyczaj
    0.48
    Activations Density 0.000%

    No Known Activations