© 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. 91518
    Prev
    Next
    INDEX
    Explanations

    names, places, foreign words

    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
     nakalista
    -0.70
     considérons
    -0.50
     calendriers
    -0.49
     liquid
    -0.48
    Datuak
    -0.48
     flat
    -0.48
     doubt
    -0.48
     ID
    -0.48
    IBAction
    -0.48
     nonUne
    -0.47
    POSITIVE LOGITS
     démocr
    0.62
    ans
    0.61
     âgées
    0.59
     vérit
    0.56
     financières
    0.54
     complètes
    0.54
     écout
    0.52
     chré
    0.52
    anair
    0.51
     avoient
    0.50
    Activations Density 0.001%

    No Known Activations