© 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. 2908
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
     Meksiku
    -0.84
     Jefus
    -0.84
     ſhe
    -0.84
     Monfieur
    -0.82
     ſche
    -0.78
     Majefty
    -0.76
     announcements
    -0.74
    RectangleBorder
    -0.74
     bends
    -0.73
     deletions
    -0.73
    POSITIVE LOGITS
    Encyklopedia
    0.44
     a
    0.42
    bufio
    0.41
    diğinde
    0.40
     keter
    0.37
     Staats
    0.37
     over
    0.35
    stasy
    0.34
    помним
    0.34
     
    0.34
    Activations Density 0.001%

    No Known Activations