© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2004
    Prev
    Next
    INDEX
    Explanations

    or

    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
    expandindo
    -0.59
    contentLoaded
    -0.52
     HasFactory
    -0.51
     bezeichneter
    -0.50
    mobileqq
    -0.48
    шње
    -0.45
     ***!
    -0.45
     vPvB
    -0.45
    DotNetBar
    -0.44
    addPreferredGap
    -0.44
    POSITIVE LOGITS
    esgue
    0.66
    MeasureSpec
    0.58
    اقت
    0.56
    MockMvc
    0.55
    StreetMap
    0.54
    וויק
    0.54
    createCanvas
    0.52
    GeneratedValue
    0.51
    asaran
    0.51
    </tfoot>
    0.50
    Activations Density 0.016%

    No Known Activations