© 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. 15517
    Prev
    Next
    INDEX
    Explanations

    references to SVG (Scalable Vector Graphics) files or elements

    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
    djangoproject
    -0.93
    enderror
    -0.88
    CascadeType
    -0.78
    Smarty
    -0.71
    tagHelperRunner
    -0.70
     Jor
    -0.70
    enumi
    -0.68
     Elisha
    -0.68
     Allociné
    -0.67
    úly
    -0.66
    POSITIVE LOGITS
    svg
    2.17
     svg
    1.74
     SVG
    1.48
     Svg
    1.44
    Svg
    1.35
    SVG
    1.31
    allenge
    0.71
    scape
    0.69
     Wirth
    0.69
     sv
    0.66
    Activations Density 0.001%

    No Known Activations