© 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. 5040
    Prev
    Next
    INDEX
    Explanations

    prevails

    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
    <bos>
    -0.88
    principalTable
    -0.53
    <tfoot>
    -0.50
    WebServlet
    -0.48
    JspWriter
    -0.48
    @[+][
    -0.47
     tartalmaz
    -0.46
     noqa
    -0.46
    GUILayout
    -0.45
     Dilution
    -0.45
    POSITIVE LOGITS
     calm
    0.57
     createSlice
    0.57
     MainAxisSize
    0.57
    onAttach
    0.57
     للمعارف
    0.57
    neté
    0.56
    ContextHolder
    0.55
     informée
    0.55
    calm
    0.54
     actionMode
    0.54
    Activations Density 0.002%

    No Known Activations