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. 14280
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "when"

    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
    /*
    -0.71
    IsPostBack
    -0.54
     snippetHide
    -0.50
    клопе
    -0.50
    endcsname
    -0.49
    +#+#
    -0.49
    </b>
    -0.46
     daqui
    -0.46
    ↵
    -0.44
    فایل‌لار
    -0.44
    POSITIVE LOGITS
     myſelf
    0.93
     purpoſe
    0.89
     Monfieur
    0.88
     itſelf
    0.86
     Jefus
    0.84
     poffe
    0.81
     ſtate
    0.80
     becauſe
    0.80
     himſelf
    0.77
     fometimes
    0.77
    Activations Density 0.314%

    No Known Activations