© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38299
    Prev
    Next
    INDEX
    Explanations

    surgical

    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
     Surgical
    -0.56
    ancio
    -0.53
    foreground
    -0.52
    URLException
    -0.50
    StackNavigator
    -0.49
    اید
    -0.48
    textAppearance
    -0.47
    providedIn
    -0.47
    PendingIntent
    -0.46
    ligne
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.81
    Personendaten
    0.75
     indisponible
    0.70
    ########.
    0.69
    MLLoader
    0.68
    TagHelper
    0.65
    ValueStyle
    0.61
    MigrationBuilder
    0.61
     Paglinawan
    0.60
    EndTag
    0.59
    Activations Density 0.141%

    No Known Activations