© 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. 3052
    Prev
    Next
    INDEX
    Explanations

    modal verbs

    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
    ########.
    -0.73
     AssemblyTitle
    -0.73
    windowFixed
    -0.69
     odkazy
    -0.68
    InstrumentedTest
    -0.67
     שוליים
    -0.64
    dafx
    -0.63
    enschappelijke
    -0.63
     MenuView
    -0.61
    GEBURTSDATUM
    -0.61
    POSITIVE LOGITS
     be
    0.65
     wireType
    0.56
     investigate
    0.44
     yii
    0.44
    ínsula
    0.43
     být
    0.43
    Be
    0.43
     tenha
    0.40
     investig
    0.40
    性を
    0.40
    Activations Density 0.019%

    No Known Activations