© 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. 39779
    Prev
    Next
    INDEX
    Explanations

    Photos

    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
    theory
    -0.76
    Theory
    -0.69
     cherchés
    -0.65
     Hail
    -0.64
     Theory
    -0.60
    مصادر
    -0.59
    shmi
    -0.58
    ACC
    -0.57
    GraphicsUnit
    -0.55
    Hail
    -0.55
    POSITIVE LOGITS
    parsedMessage
    0.74
     rejoindre
    0.59
    er
    0.57
    ombia
    0.56
     unknownFields
    0.53
    ing
    0.52
     veuillez
    0.52
     vagyok
    0.51
     protoimpl
    0.50
     rispond
    0.50
    Activations Density 1.259%

    No Known Activations