© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3292
    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
     către
    -0.60
     effectivement
    -0.58
     MainAxisSize
    -0.55
     huden
    -0.55
     réguli
    -0.53
    Everybody
    -0.52
    GMENT
    -0.51
    gæ
    -0.50
    колко
    -0.49
    dialement
    -0.49
    POSITIVE LOGITS
    sizeCache
    0.63
     risks
    0.60
     favorites
    0.58
     injuries
    0.57
     Ns
    0.57
     propOrder
    0.56
     Italijanski
    0.55
     deaths
    0.54
     Salom
    0.54
     adversity
    0.54
    Activations Density 0.005%

    No Known Activations