© 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. 5077
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     TextAlign
    -0.58
    ScopeManager
    -0.56
    ardez
    -0.56
    PRNewswire
    -0.55
    ↪
    -0.52
    WebControls
    -0.51
     Schmer
    -0.50
     sẻ
    -0.48
     InputDecoration
    -0.47
    localObject
    -0.47
    POSITIVE LOGITS
    addCriterion
    0.60
    GeoNames
    0.57
     mandal
    0.54
    écart
    0.53
     található
    0.52
    wirtschaft
    0.51
     Gaylord
    0.50
     BoxFit
    0.50
    ibatis
    0.49
     isolado
    0.49
    Activations Density 0.000%

    No Known Activations