© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3033
    Prev
    Next
    INDEX
    Explanations

    XML version declaration

    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
    WSGI
    -0.54
     căn
    -0.51
    chrän
    -0.51
    úsqueda
    -0.51
    verwijspagina
    -0.51
    tagez
    -0.49
    __(/*!
    -0.48
    Condition
    -0.48
    ed
    -0.48
    timmen
    -0.48
    POSITIVE LOGITS
    SequentialGroup
    0.59
    ChildIndex
    0.56
     defaultstate
    0.51
     gainera
    0.51
    Попис
    0.49
     antibio
    0.48
    AndEndTag
    0.48
    InjectAttribute
    0.48
    PropertyChanging
    0.48
    IsContent
    0.47
    Activations Density 0.092%

    No Known Activations