© 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. 73094
    Prev
    Next
    INDEX
    Explanations

    resource

    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
    TagMode
    -0.58
    fulness
    -0.54
    fillType
    -0.51
    ::::::::::::::::
    -0.50
    ::~
    -0.48
     onely
    -0.48
    DebuggerNonUser
    -0.47
    jali
    -0.47
    PRNewswire
    -0.46
    Me
    -0.44
    POSITIVE LOGITS
    qrstuvwxyz
    0.68
    Personendaten
    0.65
    richTextPanel
    0.64
    :✨
    0.63
     autorytatywna
    0.62
    SpringBootTest
    0.62
    contentLoaded
    0.61
     gyhoeddwyd
    0.59
    adpleegd
    0.59
     cherchés
    0.59
    Activations Density 0.001%

    No Known Activations