© 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. 23081
    Prev
    Next
    INDEX
    Explanations

    references to theoretical models and equations in the context of physics and dynamics

    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
    HideFlags
    -0.54
    ecake
    -0.52
    TagHelper
    -0.46
    setVerticalGroup
    -0.45
    RenderAtEndOf
    -0.44
     Kombat
    -0.43
     ome
    -0.43
    cetamol
    -0.43
    MockMvc
    -0.43
    Reilly
    -0.42
    POSITIVE LOGITS
    ArgsConstructor
    0.72
     Efq
    0.71
    HtmlAttribute
    0.67
    anguardia
    0.65
    Obrázky
    0.63
     Jefus
    0.62
     neceff
    0.62
     ſtate
    0.62
     becauſe
    0.61
     themſelves
    0.61
    Activations Density 0.071%

    No Known Activations