© 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. 92590
    Prev
    Next
    INDEX
    Explanations

    approvals and permissions

    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
     det
    -0.54
    lyl
    -0.54
    PerformLayout
    -0.52
    الدراسه
    -0.51
    ParallelGroup
    -0.50
     approved
    -0.48
    ̍
    -0.48
     disambiguazione
    -0.48
    UTERS
    -0.47
    juvant
    -0.47
    POSITIVE LOGITS
    amaño
    0.65
     Nacionales
    0.65
    numerusform
    0.64
     espirituales
    0.63
     clôture
    0.63
     épaules
    0.63
     définiti
    0.62
    ])));
    0.62
     zelve
    0.60
     mères
    0.59
    Activations Density 0.001%

    No Known Activations