© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14581
    Prev
    Next
    INDEX
    Explanations

    periods

    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
    DockStyle
    -0.78
    BufferException
    -0.64
    opardy
    -0.64
    RequiresApi
    -0.59
     OBITUARY
    -0.58
    transQ
    -0.58
    myspace
    -0.56
    SourceChecksum
    -0.56
    Offered
    -0.55
    ientôt
    -0.55
    POSITIVE LOGITS
     nakalista
    0.72
    клопе
    0.57
     Policy
    0.57
    ↵↵
    0.53
     But
    0.52
    fromCharCode
    0.50
     Low
    0.49
     that
    0.49
     Government
    0.47
     Oil
    0.47
    Activations Density 0.001%

    No Known Activations