© 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. 0-CLT-HP
    7. 41247
    Prev
    Next
    INDEX
    Explanations

    in

    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
     jugé
    -0.55
     vetro
    -0.52
     aveug
    -0.51
     InputDecoration
    -0.51
     dår
    -0.50
    anasia
    -0.50
     gevolg
    -0.49
    tikel
    -0.49
     graphiques
    -0.49
     Wikiseite
    -0.48
    POSITIVE LOGITS
     المعيارى
    0.81
    DoubleQuotes
    0.69
    setVerticalGroup
    0.67
     متعلقه
    0.67
    skjaer
    0.65
     AssemblyVersion
    0.62
    بوابة
    0.62
     tiguan
    0.60
    󠁣
    0.59
     שוליים
    0.59
    Activations Density 0.065%

    No Known Activations