© 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. 22-RES-MATRYOSHKA-DC
    7. 1707
    Prev
    Next
    INDEX
    Explanations

    LaTeX or code snippets with numbers, symbols and references

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     Wikipédia
    -0.60
     GIPHY
    -0.57
     assim
    -0.55
     ItemStack
    -0.54
    }\]
    -0.51
     Wikiquote
    -0.50
     PicClick
    -0.49
    ㅡ
    -0.49
     Cluj
    -0.49
     leaſt
    -0.48
    POSITIVE LOGITS
     &
    2.47
    &
    2.02
    (&
    1.49
     \&
    1.45
    }&
    1.37
    ,&
    1.35
    .&
    1.33
     (&
    1.32
    )&
    1.31
    &(
    1.23
    Activations Density 0.678%

    No Known Activations