© 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. 75076
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific documents

    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
    ↵↵
    -0.42
    .
    -0.32
    ↵
    -0.32
     penga
    -0.28
     As
    -0.28
     
    -0.28
     sein
    -0.27
    <eos>
    -0.26
     The
    -0.25
     K
    -0.24
    POSITIVE LOGITS
    oredCriteria
    1.28
     CreateTagHelper
    1.22
    parsedMessage
    1.09
     resourceCulture
    1.07
    AndEndTag
    1.05
     saites
    0.99
     Мексичка
    0.96
    ChildScrollView
    0.95
    SharedDtor
    0.95
    setVerticalGroup
    0.94
    Activations Density 0.012%

    No Known Activations