© 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. 20-CLT-HP
    7. 73179
    Prev
    Next
    INDEX
    Explanations

    6

    np_max-act-logits · 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
     nakalista
    -0.88
     propOrder
    -0.80
    
    -0.77
     препратки
    -0.71
     estimés
    -0.66
    ItemBackground
    -0.65
    didSet
    -0.63
    XmlAccessType
    -0.62
    StreetMap
    -0.62
    YLON
    -0.60
    POSITIVE LOGITS
    randrange
    0.53
     ancient
    0.50
     energy
    0.48
     numerous
    0.46
     energetically
    0.44
    czo
    0.44
     Energie
    0.42
    straint
    0.41
    alp
    0.40
     spec
    0.39
    Activations Density 0.005%

    No Known Activations