© 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. 92554
    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
    ConstraintMaker
    -0.79
    DeleteBehavior
    -0.78
     المعيارى
    -0.75
     iprot
    -0.74
    PerformLayout
    -0.71
     الحره
    -0.71
    awtextra
    -0.69
    pyplot
    -0.69
    AndEndTag
    -0.69
    onAttach
    -0.69
    POSITIVE LOGITS
    Colore
    0.45
     enged
    0.40
    ioren
    0.39
     Infrared
    0.38
     yli
    0.38
    leč
    0.38
    openhague
    0.38
     esco
    0.38
    ************/
    0.37
    menus
    0.37
    Activations Density 0.016%

    No Known Activations