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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14271
    Prev
    Next
    INDEX
    Explanations

    references to dates, times, and ages

    oai_token-act-pair · 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
    <bos>
    -1.09
    '
    -0.65
    ).
    -0.52
    ')
    -0.52
    )}
    -0.50
    ').
    -0.50
     
    -0.49
    )}{
    -0.49
     Didn
    -0.48
    '.
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.86
    帖最后由
    0.75
     كومونز
    0.67
    RegistryLite
    0.66
    parian
    0.61
     vetorial
    0.59
    SequentialGroup
    0.58
     PhpStorm
    0.58
    tainty
    0.57
     Ys
    0.57
    Activations Density 1.002%

    No Known Activations