© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs and language syntax elements

    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
     Roskov
    -0.67
    Референце
    -0.65
    //
    -0.63
    المناصب
    -0.63
    umet
    -0.63
    sibili
    -0.60
    Życiorys
    -0.60
    CloseOperation
    -0.60
    Kaynakça
    -0.60
     endwhile
    -0.60
    POSITIVE LOGITS
     commons
    0.57
     régal
    0.56
     Aquila
    0.53
     affari
    0.51
     colic
    0.51
    енча
    0.51
    extAlignment
    0.50
    tagHelperRunner
    0.50
     profondità
    0.50
     Nani
    0.50
    Activations Density 0.012%

    No Known Activations