© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 332
    Prev
    Next
    INDEX
    Explanations

    Genetic sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.54
    SupportActionBar
    -0.52
     BoxFit
    -0.48
    WithIOException
    -0.48
     Normdatei
    -0.47
    setColumns
    -0.46
     religieuses
    -0.45
    izon
    -0.43
     <<<<<<<<<<<<<<
    -0.43
    istoitu
    -0.43
    POSITIVE LOGITS
     ✭✭
    0.65
    :✨
    0.60
    Portail
    0.60
     ProtoMessage
    0.57
    ranean
    0.57
     ExecuteAsync
    0.56
     autorytatywna
    0.56
     ujednoznacz
    0.55
     anty
    0.54
    IonicModule
    0.54
    Activations Density 0.019%

    No Known Activations