© 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. 5315
    Prev
    Next
    INDEX
    Explanations

    to

    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
    eraard
    -0.47
    #
    -0.42
     peligro
    -0.39
     nôtre
    -0.36
    grà
    -0.36
    owieck
    -0.35
    =?";
    -0.35
     kiin
    -0.34
     îng
    -0.34
    MFC
    -0.33
    POSITIVE LOGITS
    IntoConstraints
    0.88
    ReusableCell
    0.81
    GraphicsUnit
    0.75
    
    0.73
     formatted
    0.68
    RenderAtEndOf
    0.66
    adaptiveStyles
    0.66
    ModelSerializer
    0.65
     modeled
    0.65
    didSet
    0.64
    Activations Density 0.003%

    No Known Activations