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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16267
    Prev
    Next
    INDEX
    Explanations

    instances of stream of consciousness writing, particularly related to feelings, the world, or war

    oai_token-act-pair · 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
    Datuak
    -0.77
     estekak
    -0.72
    Autoritní
    -0.69
     AttributeSet
    -0.62
    ArgsConstructor
    -0.60
    marginHorizontal
    -0.58
     ProtoMessage
    -0.57
    Personendaten
    -0.56
    memoized
    -0.55
     OFDb
    -0.55
    POSITIVE LOGITS
     soir
    0.52
     mountains
    0.52
     trees
    0.50
     cacti
    0.50
     neutrons
    0.50
    miary
    0.49
     desar
    0.49
     stools
    0.48
    saraba
    0.47
     balloons
    0.46
    Activations Density 6.150%

    No Known Activations