© 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. 5-CLT-HP
    7. 91948
    Prev
    Next
    INDEX
    Explanations

    required

    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
     esternos
    -0.63
     ExecuteAsync
    -0.62
     EconPapers
    -0.60
     autorytatywna
    -0.60
    InjectAttribute
    -0.59
     InputDecoration
    -0.59
    Enllaces
    -0.59
    AndEndTag
    -0.58
    SharedDtor
    -0.56
    IntoConstraints
    -0.55
    POSITIVE LOGITS
     Приступљено
    0.57
    IContainer
    0.55
    >--}}
    0.54
    huriyet
    0.53
    SCRIBE
    0.52
      (
    0.51
    ''')
    0.50
    Portail
    0.49
     question
    0.48
    studi
    0.47
    Activations Density 0.001%

    No Known Activations