© 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. 98027
    Prev
    Next
    INDEX
    Explanations

    land and earth

    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
     qualités
    -0.54
     AssemblyVersion
    -0.54
    WithMany
    -0.50
     manières
    -0.50
     وتسجيلات
    -0.49
     vermelhas
    -0.48
     bienfaits
    -0.48
    SuppressMessage
    -0.48
    addPreferredGap
    -0.48
    Hentet
    -0.48
    POSITIVE LOGITS
     batteries
    0.64
    fall
    0.63
     stations
    0.60
     installations
    0.59
     facilities
    0.58
    Rohy
    0.57
     antennas
    0.57
     EKG
    0.56
     towers
    0.55
    Batteries
    0.54
    Activations Density 0.000%

    No Known Activations