© 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. 4-CLT-HP
    7. 2067
    Prev
    Next
    INDEX
    Explanations

    period

    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
    parsedMessage
    -0.78
    ellschaft
    -0.52
    Билгалдахарш
    -0.50
    intios
    -0.50
    FieldBuilder
    -0.49
    HasForeignKey
    -0.48
    xase
    -0.48
    клопе
    -0.47
     Double
    -0.47
    requestCode
    -0.47
    POSITIVE LOGITS
    adaptiveStyles
    0.67
    Geplaatst
    0.63
     parseFrom
    0.56
    AccessorTable
    0.53
     lenker
    0.52
    ends
    0.52
    Šaltiniai
    0.50
     препратки
    0.49
    irent
    0.49
    idemia
    0.48
    Activations Density 0.040%

    No Known Activations