© 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. 2077
    Prev
    Next
    INDEX
    Explanations

    code/URLs/filenames

    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
    UserScript
    -0.62
    Портал
    -0.57
    endaftaran
    -0.53
     Cabral
    -0.52
    titch
    -0.51
    Хьажоргаш
    -0.48
    OutputType
    -0.48
     муніципалі
    -0.47
    msgTypes
    -0.47
    addCriterion
    -0.47
    POSITIVE LOGITS
     viewDidLoad
    0.53
     Mieter
    0.50
     droite
    0.48
     goûts
    0.48
    PhysRevLett
    0.48
     constitucional
    0.47
    πος
    0.46
     вікі
    0.46
     hoogte
    0.45
    MockBean
    0.45
    Activations Density 0.007%

    No Known Activations