© 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. 4657
    Prev
    Next
    INDEX
    Explanations

    plant

    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
    曖昧さ回避
    -0.66
    erne
    -0.57
    
    -0.51
    Scale
    -0.50
     Scale
    -0.49
    Mass
    -0.48
     становника
    -0.48
    igert
    -0.47
    lan
    -0.47
    ocratic
    -0.46
    POSITIVE LOGITS
     propOrder
    0.81
    DrawerToggle
    0.65
     ddelweddau
    0.65
     flower
    0.64
    ValueStyle
    0.61
    
    0.58
    contentLoaded
    0.56
    ">//
    0.55
     synthesize
    0.55
    haustible
    0.54
    Activations Density 0.001%

    No Known Activations