© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2673
    Prev
    Next
    INDEX
    Explanations

    possession or control

    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
    templateUrl
    -0.61
    ioutil
    -0.52
     OFDb
    -0.51
    ueux
    -0.50
    cuterie
    -0.49
     acredit
    -0.49
     Populations
    -0.48
     loaned
    -0.48
     queued
    -0.48
    anças
    -0.47
    POSITIVE LOGITS
    تقاوى
    0.63
     '\\;'
    0.50
     jsPsych
    0.46
     Blond
    0.46
    DockStyle
    0.45
    المناصب
    0.44
    ंदीखरीदारी
    0.44
    IntoConstraints
    0.44
     })
    
    0.43
     GetEnumerator
    0.43
    Activations Density 0.002%

    No Known Activations