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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1748
    Prev
    Next
    INDEX
    Explanations

    words that are semantically related to analysis, models, algorithms, experiments, and events

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     comunista
    -1.01
     universitaria
    -0.95
     termica
    -0.93
     aikaa
    -0.90
     spirituale
    -0.89
     définiti
    -0.88
     argint
    -0.88
     prieten
    -0.88
     echip
    -0.88
     femei
    -0.87
    POSITIVE LOGITS
     Ind
    0.62
     enf
    0.61
     Fol
    0.61
     cic
    0.60
     coe
    0.60
     fi
    0.60
    fl
    0.60
     cru
    0.59
     cá
    0.59
     Bac
    0.59
    Activations Density 81.172%

    No Known Activations