© 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. 95052
    Prev
    Next
    INDEX
    Explanations

    Top or bottom

    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
     top
    -0.62
    Top
    -0.57
     Top
    -0.54
    TOP
    -0.53
    top
    -0.53
     TOP
    -0.53
     topped
    -0.51
    GetAxis
    -0.51
     AppCompat
    -0.48
    addKeyListener
    -0.47
    POSITIVE LOGITS
    MLLoader
    0.59
    engertian
    0.56
    Geplaatst
    0.52
    новниш
    0.51
    Enllaces
    0.50
     kasarigan
    0.50
    COUVER
    0.49
     Roskov
    0.48
    EndInit
    0.47
    ยว
    0.47
    Activations Density 0.009%

    No Known Activations