© 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. 20-CLT-HP
    7. 73153
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · 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
     Efq
    -0.75
     CreateTagHelper
    -0.73
    LookAnd
    -0.72
    UnusedPrivate
    -0.69
    MENAFN
    -0.69
    WriteTagHelper
    -0.68
    ArgsConstructor
    -0.67
     '\\;'
    -0.66
     OnInit
    -0.66
    //
    -0.65
    POSITIVE LOGITS
     poll
    0.56
    Poll
    0.52
     Poll
    0.49
     tax
    0.49
    vtk
    0.49
     test
    0.48
     पा
    0.47
     Test
    0.46
     rate
    0.46
     head
    0.46
    Activations Density 0.000%

    No Known Activations