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. 14102
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time or a specific time

    oai_token-act-pair · gemini-2.0-flash

    "with" in other languages

    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
     nakalista
    -0.92
     للمعارف
    -0.76
    ########.
    -0.73
    StructEnd
    -0.72
     ujednoznacz
    -0.71
     Audiodateien
    -0.71
     surla
    -0.71
    saurus
    -0.69
    windowFixed
    -0.68
    CardModule
    -0.67
    POSITIVE LOGITS
     with
    1.88
    with
    1.38
     avec
    1.28
     dengan
    1.13
     WITH
    1.11
     với
    1.09
     With
    1.09
    With
    1.05
    กับ
    0.92
     kanssa
    0.87
    Activations Density 4.745%

    No Known Activations