© 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. 0-CLT-HP
    7. 90584
    Prev
    Next
    INDEX
    Explanations

    difference

    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
     difference
    -2.13
    difference
    -1.83
     Difference
    -1.74
    Difference
    -1.63
     DIFFERENCE
    -1.53
     différence
    -1.47
     diferença
    -1.38
     verschil
    -1.30
     differenza
    -1.28
     diferencia
    -1.19
    POSITIVE LOGITS
    帖最后由
    0.61
     of
    0.54
    migrationBuilder
    0.54
    .
    0.54
     in
    0.54
    пля
    0.53
     maker
    0.52
    DebuggerNonUser
    0.49
     to
    0.48
     for
    0.47
    Activations Density 0.051%

    No Known Activations