© 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. 5-CLT-HP
    7. 91327
    Prev
    Next
    INDEX
    Explanations

    alumni

    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
    horn
    -0.47
    ầy
    -0.45
     Hunt
    -0.45
    hörige
    -0.45
     menang
    -0.45
     him
    -0.44
     вле
    -0.43
    izarra
    -0.43
     and
    -0.43
    ภา
    -0.42
    POSITIVE LOGITS
    
    0.77
    Geplaatst
    0.75
    __':
    0.67
    جغرافيا
    0.65
     Савезне
    0.63
     FetchType
    0.62
    észetes
    0.62
     pleaſure
    0.60
     NSCoder
    0.60
    grà
    0.60
    Activations Density 0.002%

    No Known Activations