© 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. 0-CLT-HP
    7. 42201
    Prev
    Next
    INDEX
    Explanations

    medical, software downloads

    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
     Crowns
    -0.79
    uries
    -0.65
     history
    -0.62
     esimer
    -0.60
    uchi
    -0.57
    ennia
    -0.57
     tutkim
    -0.57
     spagnolo
    -0.57
     Needle
    -0.56
    håll
    -0.56
    POSITIVE LOGITS
    wahati
    0.52
    UNDP
    0.51
     الدولى
    0.50
    Referències
    0.50
    Източници
    0.48
     eventdata
    0.48
     }}"></
    0.47
    quine
    0.47
    Demografie
    0.46
    allage
    0.45
    Activations Density 0.665%

    No Known Activations