© 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. 94785
    Prev
    Next
    INDEX
    Explanations

    pas

    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
    pas
    -1.70
     pas
    -1.52
    nette
    -1.10
    Pas
    -1.02
     Pas
    -1.00
    __':
    -0.79
     PAS
    -0.67
    PAS
    -0.66
    __":
    -0.66
    }\]
    -0.65
    POSITIVE LOGITS
    DrawerToggle
    0.62
    MENAFN
    0.57
    bitField
    0.55
     ejus
    0.54
     présidenti
    0.54
     réglable
    0.53
     répondit
    0.52
    ItemBackground
    0.52
     Jurí
    0.52
     télécharge
    0.51
    Activations Density 0.378%

    No Known Activations