© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 861
    Prev
    Next
    INDEX
    Explanations

    man-made or documentation

    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
     énorme
    -0.50
     riconoscimento
    -0.50
     sorella
    -0.50
     cervello
    -0.50
     spørs
    -0.49
     tramonto
    -0.49
     precisione
    -0.49
     sonno
    -0.49
     jajaran
    -0.48
    kjø
    -0.48
    POSITIVE LOGITS
     EClass
    0.63
     AssemblyCulture
    0.60
    ioutil
    0.57
    TEMPO
    0.55
    outSlope
    0.55
     متعلقه
    0.54
     strtotime
    0.54
    writeFieldEnd
    0.53
     useRef
    0.53
     Saxons
    0.53
    Activations Density 0.026%

    No Known Activations