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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5952
    Prev
    Next
    INDEX
    Explanations

    the word "just"

    np_token-act-pair-logits · gpt-4o-mini

    the word "just"

    oai_token-act-pair · gemini-2.0-flash

    Just

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    -0.66
    CloseOperation
    -0.59
     oprot
    -0.57
    aarrggbb
    -0.57
    DllImport
    -0.56
    =?";
    -0.55
    quine
    -0.53
    ();)
    -0.52
    Хьажоргаш
    -0.50
     <>",
    -0.50
    POSITIVE LOGITS
     go
    0.69
     remember
    0.68
     know
    0.66
     choose
    0.61
     just
    0.59
     leave
    0.57
     imagine
    0.57
     today
    0.56
     send
    0.56
     try
    0.56
    Activations Density 0.745%

    No Known Activations