© 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. 18-RES-MATRYOSHKA-DC
    7. 484
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "base".

    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.18.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.18.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
     NSCoder
    -0.65
    ViewChild
    -0.62
    AddTagHelper
    -0.59
     useAppContext
    -0.57
     Drapeau
    -0.56
    Carriera
    -0.55
     financières
    -0.54
    ArrowToggle
    -0.53
     ModelRenderer
    -0.52
     religieuses
    -0.52
    POSITIVE LOGITS
    Bases
    0.96
    bases
    0.95
     BASE
    0.94
     getBase
    0.93
     bases
    0.93
     Base
    0.91
    BAS
    0.90
     BAS
    0.88
     Bases
    0.88
     base
    0.86
    Activations Density 0.490%

    No Known Activations