© 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. 4487
    Prev
    Next
    INDEX
    Explanations

    Units of measurement

    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
    InstanceState
    -0.47
    nél
    -0.47
    ůměr
    -0.45
     createState
    -0.45
     изпол
    -0.44
    fillText
    -0.44
     or
    -0.43
    より
    -0.40
    거나
    -0.40
    يانة
    -0.39
    POSITIVE LOGITS
    ----</
    0.70
    principalColumn
    0.65
     QtGui
    0.64
     gawas
    0.63
     "..\..\..\
    0.63
    terrible
    0.63
    WebServlet
    0.62
    HtmlAttribute
    0.60
    +#+
    0.60
     незавершена
    0.60
    Activations Density 0.036%

    No Known Activations