Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14134
    Prev
    Next
    INDEX
    Explanations

    the word "past" or words that frequently occur near it

    oai_token-act-pair · gemini-2.0-flash

    past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    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
     past
    -3.14
    Past
    -2.72
    past
    -2.69
     Past
    -2.50
     PAST
    -2.22
    PAST
    -1.88
     pasado
    -1.52
     Vergangenheit
    -1.45
     passado
    -1.29
    過去
    -1.27
    POSITIVE LOGITS
    MigrationBuilder
    0.71
     ioutil
    0.58
     UnityEngine
    0.57
     otomatig
    0.56
    TargetApi
    0.54
    ########.
    0.54
     continuant
    0.53
    Eloquent
    0.52
    delwed
    0.52
    Smarty
    0.51
    Activations Density 0.939%

    No Known Activations