© 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. 4-CLT-HP
    7. 4473
    Prev
    Next
    INDEX
    Explanations

    .

    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
     يتيمه
    -0.96
    ագրություններ
    -0.85
     المعيارى
    -0.83
     AssemblyCompany
    -0.72
     EconPapers
    -0.70
     חיצוניים
    -0.69
     '\\;'
    -0.69
    }*/
    -0.69
    AddHtmlAttribute
    -0.68
    setVerticalGroup
    -0.68
    POSITIVE LOGITS
    .
    0.68
    USD
    0.46
    .:
    0.44
     one
    0.43
     the
    0.42
    .+
    0.42
     only
    0.42
    Torrent
    0.41
    ._
    0.40
    4
    0.40
    Activations Density 0.001%

    No Known Activations