© 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. 92512
    Prev
    Next
    INDEX
    Explanations

    to

    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
    IndentedString
    -0.63
    thâu
    -0.60
    GEBURTSDATUM
    -0.57
    RegressionTest
    -0.56
    sizeCache
    -0.55
    principalColumn
    -0.54
    JspWriter
    -0.51
    AsUp
    -0.51
     doInBackground
    -0.50
    DispatchToProps
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.54
    Standort
    0.46
     חיצוניים
    0.46
    beitung
    0.43
     immediately
    0.42
    chik
    0.42
     re
    0.42
    NESOTA
    0.41
     then
    0.40
     instead
    0.40
    Activations Density 0.000%

    No Known Activations