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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 2113
    Prev
    Next
    INDEX
    Explanations

    clauses involving a time duration or condition

    oai_token-act-pair · gemini-2.0-flash

    until

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     when
    -0.92
     WHEN
    -0.83
    when
    -0.82
     quando
    -0.81
     когда
    -0.80
     cuando
    -0.74
     When
    -0.73
    quando
    -0.70
    When
    -0.69
    WHEN
    -0.68
    POSITIVE LOGITS
     they
    0.60
     it
    0.56
    MENAFN
    0.52
     intptr
    0.51
     we
    0.51
    BeginContext
    0.50
     there
    0.50
    PageContext
    0.48
     onBackPressed
    0.47
     Anschluss
    0.47
    Activations Density 1.145%

    No Known Activations