© 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. 1-CLT-HP
    7. 15033
    Prev
    Next
    INDEX
    Explanations

    Hunt

    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
    iser
    -0.50
    SPO
    -0.50
    ates
    -0.47
     ujednoznacz
    -0.47
    ela
    -0.44
    abestanden
    -0.44
    ("")]
    -0.44
    reactstrap
    -0.44
    ers
    -0.43
    ровок
    -0.43
    POSITIVE LOGITS
    مصادر
    0.75
    ItemBackground
    0.68
     fubject
    0.62
     himſelf
    0.60
     defire
    0.57
     Majefty
    0.57
     themſelves
    0.55
     Shakspeare
    0.54
     purpoſe
    0.54
    SizeF
    0.54
    Activations Density 0.017%

    No Known Activations