© 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. 5-CLT-HP
    7. 95009
    Prev
    Next
    INDEX
    Explanations

    cognitive functions

    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
    følgelig
    -0.59
    RenderAtEndOf
    -0.58
     vostre
    -0.51
     vostri
    -0.51
     renseignements
    -0.49
     preghi
    -0.48
     extérieurs
    -0.48
     umane
    -0.48
    MathML
    -0.47
     devenue
    -0.47
    POSITIVE LOGITS
     సౌకర్య
    0.61
     ujednoznacz
    0.59
    onHide
    0.54
     HSA
    0.52
     PSE
    0.51
     CAC
    0.51
     disambiguazione
    0.49
     APD
    0.49
     TRS
    0.49
     MPS
    0.48
    Activations Density 0.012%

    No Known Activations