© 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. 1-CLT-HP
    7. 45546
    Prev
    Next
    INDEX
    Explanations

    UB

    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
     Normdatei
    -0.78
     AssemblyTitle
    -0.78
    Manbalar
    -0.77
    setVerticalGroup
    -0.77
    /***/
    -0.74
    endphp
    -0.73
    hasMoreElements
    -0.71
     AspNetCore
    -0.70
    ✨:
    -0.70
    UnitTesting
    -0.69
    POSITIVE LOGITS
     strøm
    0.48
    sproble
    0.46
    Woo
    0.45
    eluaran
    0.43
     inalámb
    0.43
     Wot
    0.43
     Woo
    0.42
    wi
    0.42
     vähän
    0.41
    grunns
    0.40
    Activations Density 0.028%

    No Known Activations