© 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. 94147
    Prev
    Next
    INDEX
    Explanations

    services and technology

    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
     providers
    -0.85
     haven
    -0.69
     don
    -0.68
    enus
    -0.66
     operators
    -0.65
    don
    -0.60
     provider
    -0.60
    ing
    -0.58
     operator
    -0.57
     Don
    -0.57
    POSITIVE LOGITS
     automatiques
    0.84
     prochaines
    0.81
     ainfi
    0.81
     réfrig
    0.80
     définiti
    0.80
     spectateurs
    0.79
     vectorielles
    0.78
     feroit
    0.77
     étoient
    0.75
     avoient
    0.75
    Activations Density 0.182%

    No Known Activations