© 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. 91890
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    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
     we
    -0.54
     I
    -0.52
    MigrationBuilder
    -0.49
     sikkert
    -0.47
     /*#__
    -0.47
    我才
    -0.45
    我不知道
    -0.42
    BASEPATH
    -0.41
     chiffres
    -0.41
     Мексичка
    -0.40
    POSITIVE LOGITS
    principalTable
    0.82
    GEBURTSDATUM
    0.80
     itſelf
    0.66
    évaluateur
    0.65
     Efq
    0.64
    shadowOffset
    0.62
     disambiguazione
    0.60
    HasOne
    0.60
     Jefus
    0.59
    msgTypes
    0.59
    Activations Density 0.005%

    No Known Activations