© 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. 5-CLT-HP
    4. 2819
    Prev
    Next
    INDEX
    Explanations

    a

    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
     really
    -0.74
     Really
    -0.67
     any
    -0.66
    mybatisplus
    -0.63
    __':
    -0.62
    Really
    -0.60
    UserScript
    -0.60
    Appearances
    -0.59
     kasarigan
    -0.57
    really
    -0.56
    POSITIVE LOGITS
     архивлан
    0.53
     way
    0.53
    no
    0.52
    NO
    0.51
     no
    0.48
     ziren
    0.47
     Genn
    0.47
     urma
    0.46
     tarko
    0.45
    ibol
    0.45
    Activations Density 0.010%

    No Known Activations