© 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. 170
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings, especially identifiers or codes

    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
    queryInterface
    -0.72
     ModelExpression
    -0.61
     EnglishChoose
    -0.60
     Himo
    -0.60
    ništvo
    -0.60
    jsii
    -0.59
    ItemBackground
    -0.57
    цездатний
    -0.55
     mxArray
    -0.55
     @"/
    -0.54
    POSITIVE LOGITS
    0
    1.16
    ０
    0.82
    ০
    0.68
    ۰
    0.61
     zéro
    0.60
     zero
    0.59
    GeoNames
    0.58
    ۰۰
    0.58
    ₀
    0.54
    O
    0.54
    Activations Density 2.808%

    No Known Activations