© 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. 72603
    Prev
    Next
    INDEX
    Explanations

    Programming/Technical language

    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
     do
    -0.65
     CreateTagHelper
    -0.58
    AndEndTag
    -0.56
     are
    -0.52
     hiér
    -0.52
     is
    -0.50
    hadiran
    -0.50
    complexContent
    -0.50
     préc
    -0.47
    IsContent
    -0.47
    POSITIVE LOGITS
     Obrador
    0.58
     pleaſure
    0.58
     purpoſe
    0.54
    ulink
    0.52
    
    0.52
     Sprung
    0.51
     SDLK
    0.51
    UnusedPrivate
    0.51
    mest
    0.50
     PublicKey
    0.49
    Activations Density 0.009%

    No Known Activations