© 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. 10112
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by" indicating the method or means of achieving an action

    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
    StoryboardSegue
    -1.00
    fromnode
    -0.77
    ็จ
    -0.74
     betweenstory
    -0.73
     nahilalakip
    -0.70
     AttributeSet
    -0.69
    ItemBackground
    -0.65
     Paglinawan
    -0.65
    MemoryWarning
    -0.65
    ArrowToggle
    -0.63
    POSITIVE LOGITS
     Diſ
    0.61
     Мексичка
    0.56
     Sidd
    0.56
     Andra
    0.55
    vanced
    0.51
     pleaſure
    0.51
     fevere
    0.51
     Moor
    0.50
     purpoſe
    0.50
     Pergamon
    0.50
    Activations Density 0.023%

    No Known Activations