© 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. 4111
    Prev
    Next
    INDEX
    Explanations

    SVG path drawing commands

    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
    zusch
    -0.47
    eens
    -0.45
     ioutil
    -0.43
     resourceCulture
    -0.43
    BlockingQueue
    -0.43
     ц
    -0.42
     planta
    -0.42
     enca
    -0.41
     Spro
    -0.40
    </>
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.98
    SequentialGroup
    0.92
    EndContext
    0.88
    IndentedString
    0.87
    IsContent
    0.80
    ">—
    0.79
    TagMode
    0.79
    lineTo
    0.77
    oa̍t
    0.77
    ])));
    0.76
    Activations Density 0.025%

    No Known Activations