© 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. 0-CLT-HP
    7. 42415
    Prev
    Next
    INDEX
    Explanations

    legal/code documents

    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
    pez
    -1.08
     numerator
    -0.68
    fjspx
    -0.65
     Савезне
    -0.61
    tvguidetime
    -0.59
     мәкалә
    -0.52
     emis
    -0.51
    GEBURTSDATUM
    -0.50
    ErrorListener
    -0.49
    ValueStyle
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.62
     betweenstory
    0.59
     المعيارى
    0.58
    Personensuche
    0.57
     Audiodateien
    0.56
    drawSprites
    0.51
     Rest
    0.51
    BeginContext
    0.51
    jfree
    0.51
    cookieParser
    0.50
    Activations Density 0.250%

    No Known Activations