© 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. 5-CLT-HP
    7. 4618
    Prev
    Next
    INDEX
    Explanations

    this

    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
     particular
    -0.76
     kind
    -0.73
     specific
    -0.73
     type
    -0.69
     unique
    -0.66
     small
    -0.63
     tiny
    -0.60
     sort
    -0.58
     minor
    -0.57
     basic
    -0.56
    POSITIVE LOGITS
     relève
    0.61
    queryInterface
    0.58
     estekak
    0.58
     resistenza
    0.56
     marié
    0.54
    IndentedString
    0.52
    ]")]
    0.51
    +:+
    0.50
    relations
    0.50
    日閲覧
    0.50
    Activations Density 0.010%

    No Known Activations