© 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. 0-CLT-HP
    7. 91096
    Prev
    Next
    INDEX
    Explanations

    user

    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
    user
    -1.60
     user
    -1.38
    USER
    -1.13
     User
    -1.07
     USER
    -1.03
    users
    -0.99
    User
    -0.94
     usuário
    -0.93
    posed
    -0.93
     users
    -0.84
    POSITIVE LOGITS
    webElementGuid
    0.79
    adpleegd
    0.77
    WebElementEntity
    0.77
    RegressionTest
    0.75
     betweenstory
    0.68
     utafitiHapana
    0.62
    AppMethodBeat
    0.61
    Controllo
    0.61
    StructEnd
    0.60
    aronder
    0.57
    Activations Density 0.105%

    No Known Activations