© 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. 411
    Prev
    Next
    INDEX
    Explanations

    proper nouns and scientific language

    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
    — 
    -0.86
     racc
    -0.83
    findpost
    -0.77
     hoff
    -0.73
    __*/
    -0.73
     pinulongan
    -0.73
    argout
    -0.72
    rast
    -0.72
    unately
    -0.71
    pport
    -0.71
    POSITIVE LOGITS
    es
    0.93
    ele
    0.92
     noires
    0.91
    ee
    0.91
    ere
    0.89
     Neve
    0.88
    et
    0.85
     Pele
    0.85
    eb
    0.84
     étrangères
    0.83
    Activations Density 9.681%

    No Known Activations