© 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. 1-CLT-HP
    7. 10278
    Prev
    Next
    INDEX
    Explanations

    tag

    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
    principalTable
    -0.70
    phite
    -0.68
    djangoproject
    -0.68
    chka
    -0.67
    ьаж
    -0.63
     utafitiHapana
    -0.62
     MSF
    -0.61
     conduction
    -0.59
    gpl
    -0.59
     Guang
    -0.58
    POSITIVE LOGITS
    σίας
    0.50
    ıştı
    0.50
     ingresso
    0.49
     <<<<<<<<<<<<<<
    0.49
    Personensuche
    0.48
     lusso
    0.47
    CompleteListener
    0.47
    TabIndex
    0.46
    lera
    0.45
    صار
    0.42
    Activations Density 0.143%

    No Known Activations