© 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. 30898
    Prev
    Next
    INDEX
    Explanations

    numerical rankings and records within sports contexts

    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
     ring
    -0.63
    त्ति
    -0.54
     setter
    -0.52
     top
    -0.51
     Ring
    -0.49
    त्त
    -0.49
    AspNet
    -0.49
     Dup
    -0.49
     CWE
    -0.49
    Swiper
    -0.48
    POSITIVE LOGITS
    SequentialGroup
    0.81
    VersionUID
    0.71
    
    0.70
     متعلقه
    0.69
    TypedDataSet
    0.67
    }());
    0.66
    يكب
    0.66
     JpaRepository
    0.66
     cherchés
    0.65
    ValueStyle
    0.61
    Activations Density 0.010%

    No Known Activations