© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41932
    Prev
    Next
    INDEX
    Explanations

    programming/configurations

    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
     programmable
    -1.63
     Programmable
    -1.38
     فريبيس
    -0.61
    endphp
    -0.60
     متعلقه
    -0.60
     estekak
    -0.59
     '\\;'
    -0.59
    FirstResponder
    -0.56
     المعيارى
    -0.55
    __*/
    -0.52
    POSITIVE LOGITS
    ρης
    0.55
    qtype
    0.54
    yonel
    0.54
     genre
    0.53
    Miracle
    0.52
     task
    0.51
    InjectAttribute
    0.50
     MenuView
    0.50
    ahal
    0.50
    kesha
    0.50
    Activations Density 1.260%

    No Known Activations