© 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. 10720
    Prev
    Next
    INDEX
    Explanations

    data entries that follow a specific numerical format or pattern

    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
    Personensuche
    -0.68
     Ruin
    -0.66
    TagMode
    -0.65
     Contactez
    -0.63
    BagConstraints
    -0.60
     Wicidata
    -0.59
     '\\;'
    -0.59
     Attitudes
    -0.57
    ніципалі
    -0.57
     illus
    -0.57
    POSITIVE LOGITS
     @"/
    0.51
     Power
    0.51
    Power
    0.48
    <bos>
    0.45
     fallu
    0.44
     $__
    0.43
    retweeted
    0.43
    UObject
    0.43
     power
    0.43
    }*/
    0.43
    Activations Density 0.058%

    No Known Activations