© 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. 91174
    Prev
    Next
    INDEX
    Explanations

    negative experiences/legal issues

    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
    MigrationBuilder
    -0.90
    kegaard
    -0.81
     Wikimedijinoj
    -0.79
    StoryboardSegue
    -0.71
    IUrlHelper
    -0.71
    contentLoaded
    -0.63
     cavalli
    -0.61
     termica
    -0.60
    protoimpl
    -0.59
     Arjuna
    -0.59
    POSITIVE LOGITS
     pre
    0.54
    alos
    0.49
    itia
    0.47
     الحره
    0.47
     ver
    0.46
     un
    0.46
    ,\,\
    0.46
    <thead>
    0.45
    ′-
    0.45
     criterios
    0.45
    Activations Density 0.393%

    No Known Activations