© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15937
    Prev
    Next
    INDEX
    Explanations

    unified

    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
     Unified
    -1.31
     unified
    -1.28
    unified
    -1.22
     unify
    -1.14
     unification
    -1.13
    Unified
    -1.11
    UNIFIED
    -0.86
     unifying
    -0.85
    verifyException
    -0.81
     kaarangay
    -0.77
    POSITIVE LOGITS
     MIL
    0.49
    s
    0.47
     Feedback
    0.47
    MIL
    0.47
    npos
    0.46
    feedback
    0.46
    ाहरण
    0.46
    Feedback
    0.45
     insu
    0.45
    Marking
    0.44
    Activations Density 1.197%

    No Known Activations