© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94383
    Prev
    Next
    INDEX
    Explanations

    of

    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
     back
    -0.59
     Any
    -0.54
     on
    -0.52
     door
    -0.50
     Back
    -0.49
     now
    -0.47
     All
    -0.47
     upon
    -0.47
     newly
    -0.47
     cross
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.87
    featureID
    0.69
    Teaching
    0.68
     amitié
    0.67
     referenties
    0.65
    parsedMessage
    0.64
     Teaching
    0.64
    TestingModule
    0.63
    Progress
    0.62
     souffrance
    0.62
    Activations Density 0.003%

    No Known Activations