© 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. 5-CLT-HP
    7. 93264
    Prev
    Next
    INDEX
    Explanations

    AU

    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
     encephalitis
    -0.50
     الوطنيه
    -0.47
     meningitis
    -0.46
     monoc
    -0.43
     singe
    -0.41
     professionalism
    -0.41
     amnesty
    -0.40
    ap
    -0.40
     Nazare
    -0.40
     Smart
    -0.40
    POSITIVE LOGITS
     Bioaccumulative
    0.81
    intios
    0.76
    InputBorder
    0.73
     فريبيس
    0.68
     للاسماء
    0.68
    ="@+
    0.68
     invokingState
    0.68
    MemoryWarning
    0.66
     ComVisible
    0.66
    iastical
    0.65
    Activations Density 0.000%

    No Known Activations