© 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. 0-CLT-HP
    7. 92130
    Prev
    Next
    INDEX
    Explanations

    Info and data

    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
     population
    -0.69
    ücks
    -0.66
     beginnetje
    -0.64
     становника
    -0.59
     condensate
    -0.57
     Waray
    -0.57
     condens
    -0.55
    uronic
    -0.55
     hyal
    -0.55
     popu
    -0.54
    POSITIVE LOGITS
    findpost
    0.60
    enterOuterAlt
    0.57
     confronti
    0.56
     snippetHide
    0.56
     démocr
    0.56
    PMailer
    0.52
     dieux
    0.51
     genoux
    0.51
     étrangères
    0.50
     complètes
    0.50
    Activations Density 0.052%

    No Known Activations