© 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. 94652
    Prev
    Next
    INDEX
    Explanations

    Dig

    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
     dig
    -1.05
     Dig
    -0.83
    dig
    -0.82
     digging
    -0.80
    Dig
    -0.77
     dug
    -0.62
    DIG
    -0.58
     ritual
    -0.56
    Digitized
    -0.49
    älv
    -0.49
    POSITIVE LOGITS
     Monfieur
    0.84
     itſelf
    0.79
     myſelf
    0.78
     chofe
    0.76
     RIPRODUZIONE
    0.73
     fubject
    0.73
    opardy
    0.73
    )";
    0.70
     cauſe
    0.69
     neceff
    0.68
    Activations Density 0.342%

    No Known Activations