© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 355
    Prev
    Next
    INDEX
    Explanations

    the neuron seems to be identifying programming code, especially related to libraries and definitions, along with some keywords and variables.

    oai_token-act-pair · gemini-2.0-flash
    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
    Datuak
    -0.87
     &___
    -0.80
     doubtnut
    -0.72
     Exact
    -0.70
    Referências
    -0.69
     öppna
    -0.69
    ISupport
    -0.68
     PGC
    -0.68
    twimg
    -0.67
    uestion
    -0.66
    POSITIVE LOGITS
     L
    1.25
     Lohan
    1.06
    L
    1.04
     Ll
    1.00
     LS
    0.99
     Ls
    0.99
     LF
    0.98
     Л
    0.92
     l
    0.92
     LH
    0.91
    Activations Density 5.204%

    No Known Activations