© 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. 6368
    Prev
    Next
    INDEX
    Explanations

    words related to di- or did- prefixes

    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
    +#+#
    -0.86
     Krak
    -0.68
    ########.
    -0.65
    argout
    -0.64
     ModelRenderer
    -0.64
    ASTNode
    -0.64
     Oboe
    -0.63
    rawDesc
    -0.62
    RUnlock
    -0.62
    ArgsConstructor
    -0.60
    POSITIVE LOGITS
     di
    3.14
     Di
    2.84
    Di
    2.61
    di
    2.47
     DI
    2.11
    DI
    1.81
     Dib
    1.56
    Dib
    1.41
     Dip
    1.38
    diac
    1.34
    Activations Density 0.136%

    No Known Activations