© 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. 960
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    setVerticalGroup
    -1.06
     الحره
    -0.80
    
    -0.74
    StructEnd
    -0.69
    richTextPanel
    -0.69
     initComponents
    -0.66
    IUrlHelper
    -0.66
    />";
    -0.63
     CGRectMake
    -0.61
    
    -0.61
    POSITIVE LOGITS
     CWE
    0.57
    usercontent
    0.48
    UTIVE
    0.47
    culate
    0.45
    onucleotide
    0.44
    рен
    0.44
    พาะ
    0.44
    crom
    0.43
    opedic
    0.43
    cellaneous
    0.41
    Activations Density 0.004%

    No Known Activations