© 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. 91879
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    StoryboardSegue
    -1.05
     otomatig
    -0.89
     >=",
    -0.78
     Мексичка
    -0.77
     betweenstory
    -0.75
     kaarangay
    -0.74
    enderror
    -0.74
     GenerationType
    -0.73
    []
    -0.73
    triangleq
    -0.72
    POSITIVE LOGITS
     and
    0.68
     or
    0.67
     but
    0.61
     esprits
    0.57
     hombros
    0.54
     sujets
    0.48
     hombro
    0.47
     légèrement
    0.46
     appena
    0.46
     dukungan
    0.45
    Activations Density 0.001%

    No Known Activations