© 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. 338
    Prev
    Next
    INDEX
    Explanations

    instances of concluding or deciding something.

    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
    tache
    -0.71
    μία
    -0.70
     Cæsar
    -0.69
     isKindOfClass
    -0.68
     Gales
    -0.65
     Marge
    -0.65
     Marches
    -0.64
    nodeName
    -0.63
     Yap
    -0.62
    URR
    -0.62
    POSITIVE LOGITS
     therefore
    1.35
    Therefore
    1.31
    Hence
    1.30
     So
    1.30
     Therefore
    1.28
     thus
    1.27
     Hence
    1.26
    Thus
    1.25
     Thus
    1.23
     so
    1.21
    Activations Density 1.079%

    No Known Activations