© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1031
    Prev
    Next
    INDEX
    Explanations

    us

    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
     виправивши
    -0.73
    estacks
    -0.57
    はじめに
    -0.52
     Prata
    -0.52
     calendriers
    -0.49
    CCESS
    -0.49
     vaga
    -0.49
     defStyleAttr
    -0.48
    bahar
    -0.48
    κτηρισ
    -0.48
    POSITIVE LOGITS
     for
    0.65
    SharedDtor
    0.56
     exécut
    0.53
    ReusableCell
    0.52
     arşivlendi
    0.52
     henvisninger
    0.52
     fallu
    0.50
     to
    0.50
    MockMvc
    0.48
    antMatchers
    0.47
    Activations Density 0.000%

    No Known Activations