© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13846
    Prev
    Next
    INDEX
    Explanations

    strengthen

    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
     Signalez
    -0.60
     Ababa
    -0.50
     שוליים
    -0.50
     emplois
    -0.49
    dasarkan
    -0.49
    CodeAttribute
    -0.49
    WithIdentifier
    -0.49
     JpaRepository
    -0.48
     piscina
    -0.48
     ileg
    -0.47
    POSITIVE LOGITS
     the
    0.68
    <bos>
    0.68
     تضيفلها
    0.62
    ècie
    0.58
     capacity
    0.54
    parsedMessage
    0.53
     collaboration
    0.53
    ecma
    0.52
     Bic
    0.51
    IndentedString
    0.50
    Activations Density 0.018%

    No Known Activations