© 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. 28138
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols relating to equations and variables

    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
    setVerticalGroup
    -0.90
    UnsafeEnabled
    -0.75
    SequentialGroup
    -0.73
     nakalista
    -0.73
    __':
    -0.71
     sanitarias
    -0.70
     marquées
    -0.69
     quelcon
    -0.68
    ]")]
    -0.67
     particulières
    -0.67
    POSITIVE LOGITS
     affaire
    0.48
    os
    0.46
     pab
    0.44
    ніципа
    0.43
     parce
    0.43
     loro
    0.42
     effec
    0.42
     Parkway
    0.41
    #{
    0.41
     sue
    0.41
    Activations Density 0.235%

    No Known Activations