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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45114
    Prev
    Next
    INDEX
    Explanations

    else

    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
    something
    -1.48
    else
    -1.45
     something
    -1.41
     else
    -1.39
     otherwise
    -1.37
    Something
    -1.27
    otherwise
    -1.27
     altrimenti
    -1.23
    Otherwise
    -1.20
     Something
    -1.18
    POSITIVE LOGITS
    ^*)
    0.54
    mtable
    0.54
     Huxley
    0.53
     himo
    0.50
    
    0.49
    indeki
    0.49
     Ble
    0.48
     den
    0.48
    ueta
    0.48
    nachron
    0.47
    Activations Density 0.018%

    No Known Activations