© 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. 32360
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or equations to solve

    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
    XmlAccessorType
    -0.53
     solution
    -0.50
    ChildScrollView
    -0.48
    n
    -0.47
    MUT
    -0.46
     flo
    -0.46
     plat
    -0.45
    cir
    -0.45
    marino
    -0.45
    ateri
    -0.45
    POSITIVE LOGITS
     esternos
    0.79
    lihood
    0.78
    Personensuche
    0.76
     endwhile
    0.75
     >=",
    0.72
    ebenarnya
    0.69
     <>",
    0.68
     zvuky
    0.67
     Murcia
    0.67
    ^(@)
    0.66
    Activations Density 0.010%

    No Known Activations