© 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. 25395
    Prev
    Next
    INDEX
    Explanations

    instances of numerals or specific characters indicating quantities or categorizations

    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
     purpoſe
    -0.75
     myſelf
    -0.75
     ſtate
    -0.74
     whereof
    -0.73
     chofe
    -0.71
     mergeFrom
    -0.71
    DeleteMapping
    -0.69
     doInBackground
    -0.68
    thoven
    -0.66
    bkz
    -0.66
    POSITIVE LOGITS
    tagHelperRunner
    0.75
    évaluateur
    0.69
     a
    0.60
    nonatomic
    0.57
     ...
    0.53
     is
    0.49
     (
    0.47
    oneofs
    0.47
    ρί
    0.46
    migrationBuilder
    0.46
    Activations Density 0.000%

    No Known Activations