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. 74551
    Prev
    Next
    INDEX
    Explanations

    Spain

    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
    numerusform
    -0.59
     BoxFit
    -0.56
    Obrázky
    -0.54
    rosion
    -0.53
     sender
    -0.53
     Ane
    -0.51
     COLORADO
    -0.50
    headless
    -0.50
     sumpay
    -0.50
     Koko
    -0.48
    POSITIVE LOGITS
    makeText
    0.59
     Cadiz
    0.52
    ształ
    0.52
     Avila
    0.52
     Cádiz
    0.51
     Cáceres
    0.51
     Seville
    0.51
     Palma
    0.49
     esternos
    0.46
     Gij
    0.46
    Activations Density 0.001%

    No Known Activations