© 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. 91885
    Prev
    Next
    INDEX
    Explanations

    just

    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
    InputBorder
    -0.67
     oprot
    -0.54
    tamol
    -0.54
     bezeichneter
    -0.54
    VIAF
    -0.54
    Datuak
    -0.52
    romptu
    -0.49
     الحره
    -0.49
    hysema
    -0.49
     Bata
    -0.47
    POSITIVE LOGITS
    HasForeignKey
    0.65
     quite
    0.64
     Quite
    0.59
    Quite
    0.59
     Nearly
    0.57
     gynhyrchwyd
    0.54
     Grüßen
    0.53
    WriteBarrier
    0.52
    oneofs
    0.52
     nearly
    0.52
    Activations Density 0.001%

    No Known Activations