© 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. 2039
    Prev
    Next
    INDEX
    Explanations

    the phrase "long term" or "long-term" and the related word "short"

    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
     expansión
    -0.83
     expand
    -0.82
     Expand
    -0.81
     expanded
    -0.79
    saraba
    -0.79
     expansion
    -0.77
    Extent
    -0.76
     Expanding
    -0.75
    を広
    -0.74
    expand
    -0.73
    POSITIVE LOGITS
     long
    3.09
    long
    2.80
    Long
    2.73
     Long
    2.72
     LONG
    2.58
    LONG
    2.27
     longs
    1.92
     longa
    1.90
     longterm
    1.79
     longue
    1.70
    Activations Density 0.776%

    No Known Activations