© 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. 3341
    Prev
    Next
    INDEX
    Explanations

    numeric values and sequences

    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
    pherds
    -0.65
    სქოლიო
    -0.60
    Zeneca
    -0.59
     побу
    -0.58
    MessageOf
    -0.58
     immor
    -0.58
    adays
    -0.57
    SaveChangesAsync
    -0.57
     ويكيميديا
    -0.57
    ongevity
    -0.56
    POSITIVE LOGITS
    complexContent
    0.79
    Datuak
    0.72
    IBOutlet
    0.70
     uska
    0.65
    ngdoc
    0.63
     GONNA
    0.60
     gonna
    0.59
    انيف
    0.56
     resourceCulture
    0.56
     AssemblyProduct
    0.56
    Activations Density 0.138%

    No Known Activations