© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97606
    Prev
    Next
    INDEX
    Explanations

    past tense 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
     genoux
    -0.67
    Nuorodos
    -0.67
    日閲覧
    -0.64
    hyrchwyd
    -0.63
     délib
    -0.61
     prisonniers
    -0.61
     démission
    -0.60
     becauſe
    -0.60
     épaules
    -0.59
     librement
    -0.59
    POSITIVE LOGITS
    oa̍t
    0.52
     global
    0.50
    ochial
    0.50
     dass
    0.48
     actions
    0.47
     general
    0.47
    佳
    0.46
     circles
    0.46
     persons
    0.45
     products
    0.45
    Activations Density 0.008%

    No Known Activations