© 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. 5657
    Prev
    Next
    INDEX
    Explanations

    For

    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
     igång
    -0.59
    RenderAtEndOf
    -0.54
     löytyy
    -0.53
     tiegħek
    -0.53
     chercheurs
    -0.51
    FirstResponder
    -0.51
     aqueles
    -0.51
     löyty
    -0.50
     genomen
    -0.50
     térm
    -0.50
    POSITIVE LOGITS
     describing
    0.87
     calculating
    0.82
     specifying
    0.81
     expressing
    0.80
     interpreting
    0.76
     defining
    0.74
     telling
    0.73
     evaluating
    0.72
     computing
    0.71
     comparing
    0.71
    Activations Density 0.001%

    No Known Activations