Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73842
    Prev
    Next
    INDEX
    Explanations

    Actions and modifications

    np_max-act-logits · 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
     linkovi
    -0.63
    ایج
    -0.57
    expandindo
    -0.55
     LUMP
    -0.54
     Pollut
    -0.52
    née
    -0.52
    Museums
    -0.52
     متعلقه
    -0.52
    bootstrapcdn
    -0.52
     Wikiseite
    -0.51
    POSITIVE LOGITS
    ècie
    0.55
    idler
    0.54
    ersham
    0.51
    INCREF
    0.51
    antor
    0.49
     money
    0.49
     StatelessWidget
    0.49
    γραμμα
    0.49
    utia
    0.49
     e
    0.48
    Activations Density 0.001%

    No Known Activations