© 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. 5-CLT-HP
    7. 93638
    Prev
    Next
    INDEX
    Explanations

    standard

    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
     wrongly
    -0.95
     incorrectly
    -0.84
     confund
    -0.79
     mistakenly
    -0.77
     estimés
    -0.75
    SequentialGroup
    -0.75
     erroneously
    -0.74
     falschen
    -0.74
     EconPapers
    -0.73
     falsely
    -0.69
    POSITIVE LOGITS
    queryInterface
    0.48
    ges
    0.46
    ź
    0.44
     rozs
    0.43
    Gambas
    0.42
    сё
    0.41
    conten
    0.41
    المشاركات
    0.41
    DotNetBar
    0.41
     rel
    0.40
    Activations Density 0.013%

    No Known Activations