© 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. 24-RES-MATRYOSHKA-DC
    7. 539
    Prev
    Next
    INDEX
    Explanations

    image tags and figure 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.24.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.24.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
     section
    -0.60
     declarat
    -0.56
     seção
    -0.55
     sections
    -0.54
    section
    -0.54
     Abschnitt
    -0.53
     clause
    -0.52
    AndEndTag
    -0.52
     déclaration
    -0.51
    անում
    -0.51
    POSITIVE LOGITS
     width
    0.83
     png
    0.82
     image
    0.82
    png
    0.79
    includegraphics
    0.78
     img
    0.78
     images
    0.77
     PNG
    0.77
    jpg
    0.77
     Image
    0.76
    Activations Density 1.135%

    No Known Activations