© 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. 375
    Prev
    Next
    INDEX
    Explanations

    instances of the word "well" followed by a positive descriptor

    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
     BoxFit
    -0.74
    bootstrapcdn
    -0.73
    jstor
    -0.73
     مصرى
    -0.69
    annica
    -0.69
    urbing
    -0.69
    fjspx
    -0.68
    triangleq
    -0.68
    hirt
    -0.68
    friger
    -0.67
    POSITIVE LOGITS
     well
    2.83
     Well
    2.56
    well
    2.55
    Well
    2.55
     WELL
    2.53
    WELL
    2.14
     wells
    1.95
     Wells
    1.68
    wells
    1.68
     bien
    1.64
    Activations Density 0.376%

    No Known Activations