© 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. 77303
    Prev
    Next
    INDEX
    Explanations

    past-tense verbs

    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
    ViewImports
    -0.70
    thâu
    -0.66
    كونات
    -0.64
     was
    -0.59
     مشين
    -0.58
     HasFactory
    -0.58
     jsPsych
    -0.57
    WebVitals
    -0.57
    󠁣
    -0.54
    Tikang
    -0.54
    POSITIVE LOGITS
     produced
    0.68
     shaped
    0.62
     operated
    0.60
     seeded
    0.60
    IMPORTED
    0.60
     fed
    0.58
    produced
    0.58
     referrerpolicy
    0.55
     bred
    0.55
     sown
    0.54
    Activations Density 0.003%

    No Known Activations