© 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. 44013
    Prev
    Next
    INDEX
    Explanations

    ipe

    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
    sisting
    -1.12
    ing
    -0.47
    yste
    -0.47
    ipe
    -0.45
     existing
    -0.43
    рав
    -0.40
    ING
    -0.38
     relevance
    -0.38
    niku
    -0.38
    ্
    -0.38
    POSITIVE LOGITS
     виправивши
    1.00
    DockStyle
    0.92
    TestingModule
    0.80
    ItemBackground
    0.79
     vermelhas
    0.78
     Wikimedijinoj
    0.78
    AutoresizingMask
    0.78
    Rüyada
    0.77
    MigrationBuilder
    0.77
    EDEFAULT
    0.76
    Activations Density 1.743%

    No Known Activations