© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4093
    Prev
    Next
    INDEX
    Explanations

    '

    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
     astuces
    -0.55
     boî
    -0.54
     contenus
    -0.52
    cupertino
    -0.51
     élas
    -0.50
     préoccup
    -0.50
     culturelles
    -0.49
     razón
    -0.49
     Around
    -0.47
    Hau
    -0.47
    POSITIVE LOGITS
    MemoryWarning
    0.66
    ✨:
    0.65
     hObject
    0.65
    withIdentifier
    0.65
    LEncoder
    0.64
    ScopeManager
    0.63
    ReusableCell
    0.63
    imanapun
    0.63
    StoryboardSegue
    0.61
    رشف
    0.61
    Activations Density 0.003%

    No Known Activations