© 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. 4772
    Prev
    Next
    INDEX
    Explanations

    website/code references

    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
     my
    -1.02
     myself
    -0.91
    my
    -0.88
    myself
    -0.84
    我的
    -0.75
     mijn
    -0.75
    My
    -0.74
    我现在
    -0.69
     Myself
    -0.69
    Meine
    -0.68
    POSITIVE LOGITS
     Wiktionnaire
    0.60
    ערכת
    0.59
    MenuInflater
    0.54
    LabelTagHelper
    0.54
    queryInterface
    0.54
     المعيارى
    0.51
    quartered
    0.50
    DICT
    0.50
     saites
    0.49
     plads
    0.49
    Activations Density 0.008%

    No Known Activations