Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74410
    Prev
    Next
    INDEX
    Explanations

    Past participle 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
     picioare
    -0.80
     înal
    -0.70
     culoare
    -0.64
     økonom
    -0.63
     scolaires
    -0.63
     oreilles
    -0.63
     réfrig
    -0.62
     argint
    -0.62
     câte
    -0.61
     inimes
    -0.61
    POSITIVE LOGITS
     Seen
    0.93
     Been
    0.88
     obtain
    0.84
     reach
    0.81
     manage
    0.80
     Shown
    0.80
     apply
    0.80
     recover
    0.79
     introduce
    0.79
     establish
    0.78
    Activations Density 0.000%

    No Known Activations