© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11746
    Prev
    Next
    INDEX
    Explanations

    ventricular

    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
    SPATH
    -0.67
    LEncoder
    -0.50
     Amphi
    -0.50
    ViewInit
    -0.46
    ofib
    -0.46
    IsContent
    -0.46
     faim
    -0.45
    Brainz
    -0.45
    lanation
    -0.45
     nerve
    -0.44
    POSITIVE LOGITS
    IVEREF
    0.71
    MigrationBuilder
    0.62
     تضيفلها
    0.61
     '\\;'
    0.56
    webElementXpaths
    0.56
     EClass
    0.56
     ComVisible
    0.55
     bezeichneter
    0.55
     мәкал
    0.54
     '{@
    0.53
    Activations Density 0.151%

    No Known Activations