© 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. 30540
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations used in formal proofs or algorithms

    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
    httphttps
    -0.86
     Roskov
    -0.71
    ONSORED
    -0.65
    ternut
    -0.64
     createSlice
    -0.64
    ennett
    -0.62
    StoryboardSegue
    -0.61
     становника
    -0.60
    Hochspringen
    -0.60
     تضيفلها
    -0.59
    POSITIVE LOGITS
     ourselves
    0.52
     likewise
    0.51
    phorus
    0.51
     attention
    0.47
     '\\;'
    0.47
     similarly
    0.44
    Externé
    0.43
    婿
    0.43
    espèce
    0.42
     yourself
    0.42
    Activations Density 0.005%

    No Known Activations