© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    rey

    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
    rey
    -1.35
    REY
    -1.08
     stället
    -0.76
     varandra
    -0.75
     snippetHide
    -0.73
    BeginContext
    -0.63
     slutet
    -0.61
    ckså
    -0.61
    tivitas
    -0.61
     Aussicht
    -0.60
    POSITIVE LOGITS
     Ehrlich
    0.57
     drives
    0.55
    BagConstraints
    0.53
     driving
    0.52
     Ruck
    0.52
    HideFlags
    0.52
     Driving
    0.51
     }}"></
    0.50
    driving
    0.50
    <%@
    0.50
    Activations Density 0.081%

    No Known Activations