© 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. 23402
    Prev
    Next
    INDEX
    Explanations

    complex numerical expressions or mathematical structures

    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
     newOwner
    -0.71
     >=",
    -0.59
     Paglinawan
    -0.58
    UnsafeEnabled
    -0.56
     @"/
    -0.54
     EClass
    -0.52
     cháy
    -0.51
    }*/
    -0.50
    ]}>
    -0.50
    ]]=
    -0.50
    POSITIVE LOGITS
    AnimationsModule
    0.60
    ftagPool
    0.51
     Hearst
    0.50
     éto
    0.49
     natale
    0.49
     pasal
    0.49
    יך
    0.49
     utafitiHapana
    0.49
    ूरत
    0.49
     sportivo
    0.49
    Activations Density 0.087%

    No Known Activations