© 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. 4-CLT-HP
    7. 1776
    Prev
    Next
    INDEX
    Explanations

    descriptive facts

    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
    WritableDatabase
    -0.75
     thereof
    -0.66
    GOTREF
    -0.60
     AssemblyProduct
    -0.58
     consultato
    -0.57
    didSet
    -0.56
     feroit
    -0.55
     ibid
    -0.54
     Winaray
    -0.54
     InputDecoration
    -0.54
    POSITIVE LOGITS
     jsPsych
    0.72
     صوتيه
    0.60
    ]),
    0.51
    KURZBESCHREIBUNG
    0.51
    EndGlobalSection
    0.50
    )=>{
    0.49
    transQ
    0.48
    Redirection
    0.48
    monės
    0.48
     sensation
    0.47
    Activations Density 0.017%

    No Known Activations