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. 16381
    Prev
    Next
    INDEX
    Explanations

    words associated with thinking and consideration

    oai_token-act-pair · gemini-2.0-flash

    think

    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
    windowFixed
    -0.84
    IUrlHelper
    -0.66
    uxxxx
    -0.65
     defStyle
    -0.65
    ///</
    -0.65
     wireType
    -0.63
    WriteBarrier
    -0.63
    makeConstraints
    -0.61
     protoimpl
    -0.60
     Мексичка
    -0.60
    POSITIVE LOGITS
     juu
    0.47
     about
    0.45
     avanti
    0.43
     madu
    0.42
     Spes
    0.41
     žal
    0.40
    ponible
    0.39
     ſa
    0.39
    leet
    0.38
     prévention
    0.38
    Activations Density 0.549%

    No Known Activations