© 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. 10135
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical or physical principles, specifically around order and expansion

    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
     صوتيه
    -0.87
    SBATCH
    -0.74
     يتيمه
    -0.66
    ContentAsync
    -0.61
     للاسماء
    -0.61
    Obra
    -0.58
    setVerticalGroup
    -0.57
    WebMethod
    -0.57
    VersionUID
    -0.56
    dots
    -0.56
    POSITIVE LOGITS
    assé
    0.54
    SharedDtor
    0.53
     лицом
    0.49
    tencent
    0.46
     spring
    0.44
    oldown
    0.43
     thẻ
    0.43
     ролях
    0.42
    vierno
    0.42
     ense
    0.41
    Activations Density 0.010%

    No Known Activations