© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11905
    Prev
    Next
    INDEX
    Explanations

    geography

    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
     Borneo
    -1.48
    ⓧ
    -0.70
     Roskov
    -0.70
    BeginContext
    -0.69
    ValueGeneration
    -0.69
    oredCriteria
    -0.68
     كومونز
    -0.67
     tartalomajánló
    -0.65
     مرئيه
    -0.64
     שוליים
    -0.63
    POSITIVE LOGITS
    AndEndTag
    0.51
     State
    0.46
     Island
    0.46
     Function
    0.45
     function
    0.42
     island
    0.42
    Island
    0.39
     Har
    0.39
    receive
    0.39
     Sea
    0.38
    Activations Density 0.097%

    No Known Activations