© 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. 5826
    Prev
    Next
    INDEX
    Explanations

    mathematical or algebraic definitions and constructs

    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
     חיצוניים
    -0.77
     calendriers
    -0.73
    abestanden
    -0.69
     Exacts
    -0.69
     nakalista
    -0.65
    AddTagHelper
    -0.63
     autorytatywna
    -0.62
    ]=="
    -0.62
    #
    -0.61
     CATCH
    -0.58
    POSITIVE LOGITS
     chez
    0.52
    newBuilder
    0.51
    couverte
    0.49
     suggest
    0.49
    ]")]
    0.48
     ho
    0.47
     homomorphism
    0.45
     works
    0.44
    gak
    0.44
    Computed
    0.43
    Activations Density 0.211%

    No Known Activations