© 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. 15114
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly those related to variables and functions

    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
     houſe
    -0.79
     étoit
    -0.73
     avoient
    -0.73
     étoient
    -0.69
     ſtate
    -0.68
     nahilalakip
    -0.67
     uſ
    -0.67
     whoſe
    -0.66
    ItemBackground
    -0.66
    ſelf
    -0.65
    POSITIVE LOGITS
     le
    0.63
    Pozri
    0.60
    ///</
    0.56
     sp
    0.54
    endwhile
    0.53
     JLabel
    0.52
     lá
    0.50
    ByUsername
    0.50
    ngdoc
    0.50
     Ras
    0.49
    Activations Density 0.018%

    No Known Activations