© 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. 2-RES-MATRYOSHKA-DC
    7. 6933
    Prev
    Next
    INDEX
    Explanations

    references to studies or research designs

    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
    IUrlHelper
    -0.92
    enumii
    -0.87
    toHaveBeenCalled
    -0.84
    providedIn
    -0.75
    AndroidJUnit
    -0.73
     Cornish
    -0.71
    minton
    -0.70
    AddTagHelper
    -0.69
    存于互联网档案馆
    -0.69
    TextHelper
    -0.68
    POSITIVE LOGITS
     Prospective
    2.28
     prospective
    2.27
    spective
    1.99
     prospec
    1.95
     PROSPECT
    1.41
     Prospect
    1.05
     prospect
    1.03
    Prospect
    0.95
     retrospective
    0.95
     prospects
    0.92
    Activations Density 0.006%

    No Known Activations