© 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. 13093
    Prev
    Next
    INDEX
    Explanations

    Information/News/Opinions

    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
     télé
    -0.53
     rink
    -0.51
    azah
    -0.51
     webinar
    -0.51
    pectiva
    -0.50
     iran
    -0.50
    PhysRevD
    -0.50
     chip
    -0.50
    Libya
    -0.50
     MainAxisSize
    -0.50
    POSITIVE LOGITS
     متعلقه
    0.65
    ValueStyle
    0.65
    يكب
    0.63
    ImageContext
    0.58
    #+#
    0.57
    GEBURTSDATUM
    0.57
     intptr
    0.57
    fjspx
    0.56
     архивлан
    0.54
    новниш
    0.53
    Activations Density 0.011%

    No Known Activations