© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43451
    Prev
    Next
    INDEX
    Explanations

    inhibiting

    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
     насељу
    -1.09
     Normdatei
    -0.94
    LookAnd
    -0.91
    #+#
    -0.89
    MigrationBuilder
    -0.89
    featureID
    -0.88
     inhibiting
    -0.88
    ValueStyle
    -0.87
    发表于
    -0.86
    RegressionTest
    -0.85
    POSITIVE LOGITS
     irré
    0.42
     transfer
    0.42
    रण
    0.42
     assignment
    0.42
    ak
    0.41
    Exped
    0.41
    き
    0.39
    hag
    0.39
    abang
    0.39
     действия
    0.38
    Activations Density 0.089%

    No Known Activations