© 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. 98023
    Prev
    Next
    INDEX
    Explanations

    Gopal

    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
    AddHtmlAttribute
    -0.68
    tvguidetime
    -0.60
    setViewportView
    -0.58
     autorytatywna
    -0.57
    AddTagHelper
    -0.52
     doInBackground
    -0.51
     estekak
    -0.50
    ContentAsync
    -0.50
    getColumnIndex
    -0.49
     kasarigan
    -0.48
    POSITIVE LOGITS
    hale
    0.66
    ulas
    0.63
    ula
    0.59
    ulam
    0.58
    ak
    0.56
    arnes
    0.52
    halen
    0.51
    ulan
    0.51
    hnen
    0.51
     članak
    0.49
    Activations Density 0.002%

    No Known Activations