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. 5940
    Prev
    Next
    INDEX
    Explanations

    the file extensions '.java' and any tokens containing the string 'antlr'

    oai_token-act-pair · gemini-2.0-flash

    uncommon foreign phrases or terms

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

    punctuation

    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
    PMailer
    -0.67
     defaultstate
    -0.66
     HttpHeaders
    -0.65
     <<<<<<<<<<<<<<
    -0.65
    Открыть
    -0.60
    
    -0.60
    abaret
    -0.59
    ushima
    -0.55
    Autoritní
    -0.55
    passport
    -0.54
    POSITIVE LOGITS
    ########.
    0.52
    Salut
    0.46
     оригіналу
    0.44
     نف
    0.44
     gomma
    0.43
     Salut
    0.42
     Mérida
    0.42
    stdlib
    0.41
     obstante
    0.41
    anglès
    0.41
    Activations Density 0.630%

    No Known Activations