© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4793
    Prev
    Next
    INDEX
    Explanations

    local

    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
     reach
    -0.81
     catch
    -0.80
     stay
    -0.68
     gain
    -0.67
     break
    -0.67
     recoup
    -0.66
     to
    -0.66
     return
    -0.66
     cope
    -0.66
     recover
    -0.65
    POSITIVE LOGITS
    сылкі
    0.58
    LayoutStyle
    0.58
     resourceCulture
    0.56
    elemField
    0.56
    AddHtmlAttribute
    0.54
     NSCoder
    0.52
    Enllaces
    0.52
    makeText
    0.51
     réguli
    0.48
    SuccessListener
    0.48
    Activations Density 0.002%

    No Known Activations