© 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. 3-RES-MATRYOSHKA-DC
    7. 3080
    Prev
    Next
    INDEX
    Explanations

    the word "ultimately," possibly when adjacent to a verb

    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
    νό
    -0.63
    atik
    -0.61
     last
    -0.60
    valido
    -0.57
    gede
    -0.56
    ό
    -0.56
     vu
    -0.53
    ≅
    -0.52
    noin
    -0.50
    last
    -0.50
    POSITIVE LOGITS
     eventually
    2.77
    Eventually
    2.70
     Eventually
    2.67
    eventually
    2.66
     ultimately
    2.59
     Ultimately
    2.48
    Ultimately
    2.42
     eventual
    2.25
     uiteindelijk
    2.17
     ultimate
    1.94
    Activations Density 0.026%

    No Known Activations