© 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. 20-CLT-HP
    7. 77224
    Prev
    Next
    INDEX
    Explanations

    passive voice

    np_max-act-logits · 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
    MigrationBuilder
    -0.53
    BeginInit
    -0.52
    httphttps
    -0.50
     Goode
    -0.48
    DialogInterface
    -0.48
    CppMethod
    -0.47
     Rae
    -0.46
    COUVER
    -0.46
    RegressionTest
    -0.46
    ndale
    -0.46
    POSITIVE LOGITS
     testifying
    0.60
     coming
    0.58
     imageNamed
    0.56
    styleType
    0.50
     relat
    0.50
    érieurs
    0.50
    SharedDtor
    0.50
     reporting
    0.49
     undersigned
    0.48
     manufact
    0.47
    Activations Density 0.000%

    No Known Activations