© 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. 13062
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    abdominal
    -1.20
    nities
    -0.75
     تانيه
    -0.56
    ExecuteReader
    -0.54
    uksi
    -0.54
    kloped
    -0.52
    BURGH
    -0.52
     biß
    -0.52
    Życiorys
    -0.50
    ToInt
    -0.48
    POSITIVE LOGITS
    ритори
    0.65
    SharedDtor
    0.63
    AccessorTable
    0.57
     Wikimedijinoj
    0.56
     IOError
    0.52
     ſmall
    0.51
    PropertyChanging
    0.50
    Diweddarwch
    0.49
     houſe
    0.49
     clearColor
    0.49
    Activations Density 0.023%

    No Known Activations