© 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. 91235
    Prev
    Next
    INDEX
    Explanations

    computer code/technology

    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
    WebElementEntity
    -0.44
     schle
    -0.42
     spr
    -0.41
    NINGS
    -0.41
     var
    -0.40
     cardinal
    -0.40
     individual
    -0.40
    ירת
    -0.40
    mousemove
    -0.39
     soll
    -0.39
    POSITIVE LOGITS
     nôtre
    0.68
     AssemblyTitle
    0.64
     mijne
    0.60
    udayaan
    0.58
    BASEPATH
    0.58
     ivelany
    0.58
    expandindo
    0.57
     niitä
    0.56
    OGND
    0.56
    abetes
    0.56
    Activations Density 0.001%

    No Known Activations