© 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. 152
    Prev
    Next
    INDEX
    Explanations

    formatted sequences of horizontal lines

    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
     שוליים
    -0.92
    homonymie
    -0.88
    IndentedString
    -0.87
    GraphicsUnit
    -0.81
     disambiguazione
    -0.80
    sizeCache
    -0.80
    !*\
    -0.80
     /\.
    -0.79
    ⓘ
    -0.79
     архивлан
    -0.78
    POSITIVE LOGITS
    ----------------
    4.06
    ================
    2.47
    ****************
    2.28
    ---------------
    2.16
    ————————————————
    1.99
    ------------
    1.84
    ################
    1.76
    --------------
    1.75
    -------------
    1.74
    ————————
    1.73
    Activations Density 1.650%

    No Known Activations