© 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. 32617
    Prev
    Next
    INDEX
    Explanations

    quantitative measures related to rankings or prevalence in various contexts

    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
     ſeveral
    -0.84
    abestanden
    -0.83
     houſe
    -0.77
    spesies
    -0.77
    loài
    -0.76
     '\\;'
    -0.76
     ſtre
    -0.75
     ſtate
    -0.75
     himſelf
    -0.74
     ſtand
    -0.74
    POSITIVE LOGITS
    仕方
    0.52
    Билгалдахарш
    0.49
    CloseOperation
    0.47
    oa̍t
    0.46
     legen
    0.46
    ViewImports
    0.43
    效
    0.42
    zarchiwizowane
    0.40
     O
    0.40
    Howdy
    0.40
    Activations Density 0.022%

    No Known Activations