© 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. 4882
    Prev
    Next
    INDEX
    Explanations

    King

    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
    /***/
    -0.67
     within
    -0.63
    gdx
    -0.61
     of
    -0.60
    d
    -0.59
    iibo
    -0.56
    n
    -0.55
     in
    -0.54
     MenuView
    -0.54
    o
    -0.53
    POSITIVE LOGITS
    bootstrapcdn
    0.74
     سكانية
    0.62
     Савезне
    0.60
    contentLoaded
    0.58
    Hochspringen
    0.56
     purpoſe
    0.56
     pleaſure
    0.56
     houſe
    0.54
    ValueStyle
    0.50
     Anſ
    0.49
    Activations Density 0.001%

    No Known Activations