© 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. 0-CLT-HP
    4. 43942
    Prev
    Next
    INDEX
    Explanations

    parents

    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
     parents
    -2.06
     Parents
    -1.72
     parent
    -1.65
    Parents
    -1.60
     Parent
    -1.53
    parents
    -1.47
    Parent
    -1.35
     ouders
    -1.30
    parent
    -1.27
     Eltern
    -1.26
    POSITIVE LOGITS
     الحره
    0.79
     متعلقه
    0.72
     Normdatei
    0.69
    agerie
    0.67
     يتيمه
    0.65
    ropoda
    0.65
    ViewInit
    0.65
    )))));
    0.64
    nachron
    0.63
     photolibrary
    0.63
    Activations Density 0.331%

    No Known Activations