Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16272
    Prev
    Next
    INDEX
    Explanations

    HTML code related to internet URLs, specifically from Twitter.

    oai_token-act-pair · gemini-2.0-flash

    URLs

    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
    :✨
    -0.58
    phism
    -0.51
     khối
    -0.47
    الإنجليزية
    -0.46
    vinte
    -0.46
     יְ
    -0.45
     Kette
    -0.45
     Filed
    -0.45
    Exited
    -0.44
     verfü
    -0.43
    POSITIVE LOGITS
     Signalez
    0.82
     cherchés
    0.69
    addCriterion
    0.68
     &___
    0.63
    ]));
    
    0.59
     invokingState
    0.59
    }")
    
    0.59
    iterranée
    0.59
     ProtoMessage
    0.58
     estekak
    0.57
    Activations Density 0.206%

    No Known Activations