© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26097
    Prev
    Next
    INDEX
    Explanations

    structural elements and parameters in programming or data 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
    出版年
    -0.80
     Efq
    -0.68
     nucléaire
    -0.61
     Jefus
    -0.60
     duquel
    -0.60
     pitié
    -0.60
     becauſe
    -0.58
     Majefty
    -0.58
     juger
    -0.57
     ſaid
    -0.57
    POSITIVE LOGITS
    :✨
    0.77
     للمعارف
    0.73
    PreferredItem
    0.65
    photobucket
    0.64
    InitVars
    0.62
    RepeatedField
    0.60
     rech
    0.57
    StructEnd
    0.56
    PerformLayout
    0.56
    ChildScrollView
    0.53
    Activations Density 0.135%

    No Known Activations