© 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. 15802
    Prev
    Next
    INDEX
    Explanations

    references to the current study or article and its findings

    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
     resourceCulture
    -1.03
     propOrder
    -1.02
    MigrationBuilder
    -0.92
    CodeAttribute
    -0.84
    StoryboardSegue
    -0.84
    SharedDtor
    -0.84
    Datuak
    -0.79
     Normdatei
    -0.79
     NSCoder
    -0.78
    Personendaten
    -0.77
    POSITIVE LOGITS
    ParallelGroup
    0.50
     intermittently
    0.43
     deployed
    0.41
     homicidio
    0.41
     potře
    0.40
     hung
    0.40
    UALA
    0.39
    remel
    0.39
    rensa
    0.39
    umumkan
    0.38
    Activations Density 0.012%

    No Known Activations