© 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. 92521
    Prev
    Next
    INDEX
    Explanations

    free

    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
     librement
    -0.75
     libremente
    -0.65
     aanwezig
    -0.61
     respectivement
    -0.60
     précie
    -0.59
     particularmente
    -0.58
     communs
    -0.57
     betrekking
    -0.56
    ReusableCell
    -0.55
     lontano
    -0.54
    POSITIVE LOGITS
    veratrol
    0.54
    talen
    0.50
    lacian
    0.50
     Neighbors
    0.49
    AddTagHelper
    0.49
     Walls
    0.47
    lon
    0.47
     version
    0.47
    Попис
    0.46
     Rail
    0.45
    Activations Density 0.002%

    No Known Activations