© 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. 4-CLT-HP
    7. 1002
    Prev
    Next
    INDEX
    Explanations

    code/errors, other language

    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
    μί
    -0.51
     sekal
    -0.50
    NESOTA
    -0.49
    antasy
    -0.49
     ['./
    -0.46
    ESTAMP
    -0.46
    ///
    -0.46
    enseits
    -0.45
     Managerial
    -0.45
    tals
    -0.45
    POSITIVE LOGITS
    principalColumn
    0.64
     CreateTagHelper
    0.63
     onCreateView
    0.60
    stateProvider
    0.60
    Collegamenti
    0.58
     Paglinawan
    0.56
     InputDecoration
    0.56
     uintptr
    0.54
    Koordinaten
    0.51
    canActivate
    0.50
    Activations Density 0.003%

    No Known Activations