© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 91869
    Prev
    Next
    INDEX
    Explanations

    titles

    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
     of
    -0.74
    <>();
    
    -0.54
    |}{$
    -0.47
     ?>/
    -0.45
    "):
    
    -0.45
    reszcie
    -0.45
    <>("
    -0.45
     OF
    -0.44
    foly
    -0.44
    ofthe
    -0.44
    POSITIVE LOGITS
    ,
    1.02
    AddTagHelper
    0.63
    expandindo
    0.59
     للاسماء
    0.58
     was
    0.58
     is
    0.57
     remarked
    0.56
     said
    0.55
     تضيفلها
    0.55
     blames
    0.54
    Activations Density 0.004%

    No Known Activations