© 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. 77220
    Prev
    Next
    INDEX
    Explanations

    Code/metadata snippets

    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
     intptr
    -0.45
    amerikanischer
    -0.39
    usz
    -0.37
     rayon
    -0.37
    remel
    -0.37
    Size
    -0.37
    évaluateur
    -0.36
     Size
    -0.36
     size
    -0.35
    anii
    -0.34
    POSITIVE LOGITS
    setVerticalGroup
    0.71
    AndEndTag
    0.69
     createSprite
    0.68
     '\\;'
    0.66
    IsContent
    0.65
    qtype
    0.65
     surla
    0.64
    DoubleQuotes
    0.63
    WebServlet
    0.61
     AssemblyCulture
    0.61
    Activations Density 0.006%

    No Known Activations