© 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. 4522
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Мексичка
    -0.70
    rungsseite
    -0.62
    دانشنامهٔ
    -0.54
    LoadScene
    -0.49
    lishes
    -0.49
    aults
    -0.49
    uebe
    -0.48
    Gemeinden
    -0.47
     calendriers
    -0.46
    CppCodeGen
    -0.46
    POSITIVE LOGITS
     will
    0.72
     deseos
    0.57
     intentions
    0.57
    MLLoader
    0.56
     intention
    0.55
    gnore
    0.54
    GEBURTSDATUM
    0.53
     wishes
    0.52
     vision
    0.50
     recommendation
    0.50
    Activations Density 0.006%

    No Known Activations