© 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. 20-CLT-HP
    7. 76430
    Prev
    Next
    INDEX
    Explanations

    Geographical locations

    np_max-act-logits · 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
     north
    -1.53
    north
    -1.40
     Northern
    -1.39
     northern
    -1.35
    North
    -1.33
     North
    -1.33
    Northern
    -1.33
    northern
    -1.32
     NORTH
    -1.31
    NORTH
    -1.30
    POSITIVE LOGITS
    numerusform
    0.39
    ἰ
    0.36
    illons
    0.36
     CURIAM
    0.36
    typeorm
    0.33
    signable
    0.32
    SocketChannel
    0.32
    simage
    0.32
     fallow
    0.32
     Cuerpo
    0.32
    Activations Density 0.008%

    No Known Activations