© 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. 5-CLT-HP
    7. 96466
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     AssemblyTitle
    -0.65
    ⓧ
    -0.59
    IsPostBack
    -0.57
     kasarigan
    -0.56
     <>",
    -0.56
     she
    -0.54
     morire
    -0.53
    AutoField
    -0.52
    OGND
    -0.52
    </thead>
    -0.52
    POSITIVE LOGITS
    MemoryWarning
    0.59
     <<<<<<<<<<<<<<
    0.50
    AnchorStyles
    0.50
    TestingModule
    0.47
     twins
    0.47
    hawa
    0.46
     Référence
    0.45
     twin
    0.45
    ufel
    0.45
    UserScript
    0.45
    Activations Density 0.001%

    No Known Activations