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. 1552
    Prev
    Next
    INDEX
    Explanations

    words that are negative or describe a difficult situation

    oai_token-act-pair · gemini-2.0-flash

    Difficult/negative situations

    np_max-act-logits · 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
    SBATCH
    -0.48
    ControllerAdvice
    -0.41
    GetField
    -0.38
    صح
    -0.37
     accett
    -0.36
    кипедия
    -0.36
    InteropServices
    -0.35
    Jîn
    -0.35
    golang
    -0.35
    getResultList
    -0.35
    POSITIVE LOGITS
    kháu
    0.90
    tagext
    0.80
    PerformLayout
    0.77
    EndContext
    0.73
    GOTREF
    0.67
    ंदीखरीदारी
    0.65
    SourceChecksum
    0.63
     noDo
    0.61
    AccessorTable
    0.60
     ویکی‌پدیا
    0.60
    Activations Density 11.678%

    No Known Activations