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. 14149
    Prev
    Next
    INDEX
    Explanations

    the word "why"

    oai_token-act-pair · gemini-2.0-flash

    why

    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
    ])));
    -0.75
     unary
    -0.74
     Thule
    -0.72
     Devonian
    -0.71
    StructEnd
    -0.71
     Pyrene
    -0.70
    setVerticalGroup
    -0.69
    UserScript
    -0.69
     handker
    -0.68
    )++;
    -0.68
    POSITIVE LOGITS
     I
    0.75
     
    0.71
     the
    0.63
     it
    0.63
     a
    0.59
     so
    0.58
    <bos>
    0.57
    I
    0.56
     So
    0.54
    So
    0.51
    Activations Density 0.130%

    No Known Activations