© 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. 1-RES-MATRYOSHKA-DC
    7. 198
    Prev
    Next
    INDEX
    Explanations

    references to a specific analytical or computational technique

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -1.14
     يتيمه
    -0.88
    tagext
    -0.83
    ftagPool
    -0.75
    ViewFeatures
    -0.73
    DataAnnotations
    -0.72
    DataSnapshot
    -0.70
    KommentareTeilen
    -0.69
    Personensuche
    -0.69
    awtextra
    -0.69
    POSITIVE LOGITS
     method
    4.25
     Method
    3.95
    method
    3.88
    Method
    3.73
     methods
    3.67
     METHOD
    3.58
     Methods
    3.45
    methods
    3.30
     méthode
    3.28
    METHOD
    3.23
    Activations Density 0.816%

    No Known Activations