© 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. 6-RES-MATRYOSHKA-DC
    7. 1029
    Prev
    Next
    INDEX
    Explanations

    words from diverse subjects like genetics, worship, math, geography, and computer code

    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
     betweenstory
    -0.77
     AllAfrica
    -0.76
     MonoBehaviour
    -0.74
    ritsar
    -0.74
    Życiorys
    -0.73
     kasarigan
    -0.71
    SQLException
    -0.71
     Wilkins
    -0.71
    VAO
    -0.71
     synap
    -0.69
    POSITIVE LOGITS
    ded
    1.14
    gd
    0.94
    td
    0.93
    rid
    0.92
    rd
    0.91
     POD
    0.91
    sd
    0.91
     Idd
    0.90
    jad
    0.89
     PED
    0.89
    Activations Density 3.572%

    No Known Activations