© 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. 20019
    Prev
    Next
    INDEX
    Explanations

    timestamp or versioning data in structured formats

    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
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.68
    พาะ
    -0.58
    ⎩
    -0.55
    pektor
    -0.54
    ensus
    -0.53
    estion
    -0.53
     mật
    -0.53
    Вопрос
    -0.53
     htmlFor
    -0.52
    gelöst
    -0.52
    POSITIVE LOGITS
     Zwick
    0.53
    sizeCache
    0.52
     irre
    0.51
    arResult
    0.50
     Âge
    0.49
    ginous
    0.44
     Plas
    0.44
    Ecc
    0.44
    Gua
    0.42
    Népesség
    0.42
    Activations Density 0.027%

    No Known Activations