© 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. 104
    Prev
    Next
    INDEX
    Explanations

    references to identifying or classifying people or objects

    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
    共に
    -1.00
    使用する
    -0.99
     następnie
    -0.93
     erneut
    -0.89
     tevens
    -0.89
    際は
    -0.87
     및
    -0.86
     می‌باشد
    -0.85
     oluşan
    -0.85
     utilizzata
    -0.84
    POSITIVE LOGITS
     thing
    1.37
     way
    1.29
     things
    1.29
     really
    1.20
    things
    1.15
     good
    1.07
     enough
    1.05
     trouble
    1.05
     somebody
    1.02
     little
    1.00
    Activations Density 20.955%

    No Known Activations