© 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. 1-CLT-HP
    7. 12094
    Prev
    Next
    INDEX
    Explanations

    disease

    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
    homonymie
    -0.55
     otomatig
    -0.53
    ագրություններ
    -0.53
    Халык
    -0.49
     FetchType
    -0.49
     nào
    -0.48
    schild
    -0.48
     lámina
    -0.48
    lorette
    -0.47
     snippetHide
    -0.47
    POSITIVE LOGITS
    <bos>
    0.64
     بيها
    0.62
     predeceased
    0.58
    PreExecute
    0.56
     indisponible
    0.56
     intervened
    0.55
    ioutil
    0.55
    onActivityResult
    0.54
    permum
    0.52
     provoked
    0.51
    Activations Density 0.128%

    No Known Activations