© 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. 4-CLT-HP
    7. 1469
    Prev
    Next
    INDEX
    Explanations

    to

    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
     pleaſure
    -0.69
    setVerticalGroup
    -0.69
     Monfieur
    -0.69
     houſe
    -0.66
     myſelf
    -0.64
     beſt
    -0.64
     purpoſe
    -0.62
     betweenstory
    -0.60
     raiſ
    -0.60
    جغرافيا
    -0.60
    POSITIVE LOGITS
    Autoritní
    0.52
    Personensuche
    0.50
     autorytatywna
    0.48
    voet
    0.45
    miştir
    0.43
     nu
    0.43
    ENING
    0.43
    ubuntu
    0.43
     z
    0.43
     in
    0.42
    Activations Density 0.000%

    No Known Activations