© 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. 91606
    Prev
    Next
    INDEX
    Explanations

    ).

    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
    іо
    -0.58
     traités
    -0.52
     colorir
    -0.52
     herren
    -0.50
     réessayer
    -0.50
    gery
    -0.50
     jeunesse
    -0.49
     avvic
    -0.49
     ampliamente
    -0.49
     Normdatei
    -0.48
    POSITIVE LOGITS
     FetchType
    0.59
    <?
    0.57
    MemoryWarning
    0.57
     estimés
    0.56
     site
    0.52
    RESUMO
    0.51
    ensement
    0.51
    expandindo
    0.50
     sit
    0.49
     Gret
    0.49
    Activations Density 0.000%

    No Known Activations