© 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. 6287
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and specific references to formulas involving variables and operations

    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
     dragón
    -0.53
    Rüyada
    -0.52
    riwal
    -0.52
    Rasp
    -0.50
     autorytatywna
    -0.49
     HomeComponent
    -0.48
    TestingModule
    -0.48
     <<<<<<<<<<<<<<
    -0.48
     presidencial
    -0.47
     voeten
    -0.47
    POSITIVE LOGITS
    存于互联网档案馆
    0.68
    MemoryWarning
    0.62
    Geplaatst
    0.56
    脚注の使い方
    0.52
    \}_{
    0.50
    ங்கள
    0.50
    ,:),
    0.48
    äten
    0.48
     varying
    0.47
    coledì
    0.47
    Activations Density 0.628%

    No Known Activations