© 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. 5-CLT-HP
    7. 2846
    Prev
    Next
    INDEX
    Explanations

    Defining and assessing

    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
    ValueStyle
    -1.08
    yntaxException
    -0.85
    parsedMessage
    -0.84
    abestanden
    -0.82
    ArgsConstructor
    -0.82
     propOrder
    -0.80
    RetentionPolicy
    -0.79
     ModelExpression
    -0.77
     فريبيس
    -0.77
     kasarigan
    -0.76
    POSITIVE LOGITS
     or
    0.60
     something
    0.55
     the
    0.55
     but
    0.50
     what
    0.49
     a
    0.47
     exactly
    0.47
     ''
    0.46
     ”
    0.46
     چیزی
    0.46
    Activations Density 0.002%

    No Known Activations