© 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. 727
    Prev
    Next
    INDEX
    Explanations

    XML files

    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
     MainAxisSize
    -0.86
     transfieras
    -0.85
     CreateTagHelper
    -0.85
     snippetHide
    -0.79
    AddTagHelper
    -0.79
     فريبيس
    -0.79
     BoxDecoration
    -0.77
    lapsingToolbar
    -0.72
    InvalidProtocol
    -0.70
    endphp
    -0.70
    POSITIVE LOGITS
    瞎
    0.47
    ectoria
    0.43
     mezzo
    0.43
    :
    0.42
     surat
    0.42
    jabat
    0.39
    rslt
    0.39
     inté
    0.39
    不忘
    0.38
     mga
    0.38
    Activations Density 0.009%

    No Known Activations