© 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. 0-CLT-HP
    7. 42340
    Prev
    Next
    INDEX
    Explanations

    Legal/formal documents

    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
     talks
    -0.65
     levis
    -0.51
     Vå
    -0.50
    Wikis
    -0.49
    borderSide
    -0.49
     mortem
    -0.49
    idosis
    -0.48
     bores
    -0.48
    Talks
    -0.47
     underv
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.91
    tonsoft
    0.71
    JspWriter
    0.71
     Vikipedi
    0.70
     eventdata
    0.68
     EClass
    0.68
    CloseOperation
    0.63
     שוליים
    0.63
    UnusedPrivate
    0.61
    gorithm
    0.60
    Activations Density 0.121%

    No Known Activations