© 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. 91498
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     labours
    -0.59
    ghana
    -0.56
    Labour
    -0.55
     labour
    -0.52
     onely
    -0.50
    tagez
    -0.49
     tyres
    -0.49
    labour
    -0.49
     Vapour
    -0.48
    DNEY
    -0.48
    POSITIVE LOGITS
    发表于
    0.63
    ineno
    0.63
    جغرافيا
    0.62
    XmlAccessorType
    0.61
    帖最后由
    0.60
     kvinder
    0.58
     متعلقه
    0.57
     Arizona
    0.57
    SharedCtor
    0.57
     Mesa
    0.56
    Activations Density 0.017%

    No Known Activations