© 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. 4136
    Prev
    Next
    INDEX
    Explanations

    references to graph plotting commands and related visualization code

    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
    ex
    -0.67
     ex
    -0.66
     doInBackground
    -0.66
     Ex
    -0.63
    DeleteBehavior
    -0.62
     GenerationType
    -0.60
    اریخ
    -0.59
     BrowserModule
    -0.59
    Ex
    -0.58
     مشين
    -0.57
    POSITIVE LOGITS
    xy
    2.33
    XY
    1.95
     xy
    1.83
     XY
    1.55
    Xy
    1.50
    xic
    1.34
     Xy
    1.32
    xi
    1.31
    oxy
    1.25
    XL
    1.17
    Activations Density 0.069%

    No Known Activations