© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14768
    Prev
    Next
    INDEX
    Explanations

    cellulose, aga

    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
    aga
    -1.83
    AGA
    -1.50
    agas
    -1.45
     cellulose
    -0.98
     Cellulose
    -0.91
    cellulose
    -0.87
    agam
    -0.77
    ulose
    -0.71
     Aga
    -0.68
     AGA
    -0.63
    POSITIVE LOGITS
     виправивши
    0.64
    IsContent
    0.60
    WebVitals
    0.59
    onAttach
    0.57
    openzeppelin
    0.57
    hasMoreElements
    0.55
     Houſe
    0.54
    HasAnnotation
    0.53
    tır
    0.52
    SpringBootTest
    0.52
    Activations Density 0.015%

    No Known Activations