© 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. 1692
    Prev
    Next
    INDEX
    Explanations

    the word "future"

    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
     assumption
    -0.68
    bably
    -0.67
    umptions
    -0.66
    Tembelea
    -0.66
     предпо
    -0.62
     assumed
    -0.62
     guessed
    -0.61
     supposition
    -0.61
    ductory
    -0.59
    PROB
    -0.59
    POSITIVE LOGITS
     future
    2.67
    future
    2.42
    Future
    2.28
     FUTURE
    2.25
     potential
    2.22
     Future
    2.22
    FUTURE
    2.22
    Potential
    2.08
     Potential
    2.02
    potential
    2.02
    Activations Density 0.270%

    No Known Activations