© 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. 91667
    Prev
    Next
    INDEX
    Explanations

    carefully

    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
    ftagPool
    -0.73
     habet
    -0.62
     Meksiku
    -0.58
     OFDb
    -0.54
    ]$}
    -0.54
    kháu
    -0.53
    avadoc
    -0.52
     Nación
    -0.51
    contentLoaded
    -0.51
     getItemId
    -0.51
    POSITIVE LOGITS
    ptonshire
    0.57
     bevor
    0.55
     before
    0.54
     sebelum
    0.54
    avance
    0.54
     CreateTagHelper
    0.51
    before
    0.49
     antes
    0.48
    Sebelum
    0.47
    subplots
    0.47
    Activations Density 0.001%

    No Known Activations