© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44181
    Prev
    Next
    INDEX
    Explanations

    sub words and stressors

    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
     européennes
    -0.74
     publiques
    -0.70
     religieuses
    -0.66
     educativas
    -0.65
     humaines
    -0.64
     umana
    -0.63
     umane
    -0.62
     vectorielles
    -0.61
     stressors
    -0.61
     polaire
    -0.61
    POSITIVE LOGITS
     NSError
    0.71
     Meksiku
    0.65
     beginnetje
    0.64
     يتيمه
    0.62
    Lähde
    0.61
    makeText
    0.59
     विश्वसनीयता
    0.59
     rev
    0.59
    leſs
    0.58
     Houd
    0.57
    Activations Density 1.962%

    No Known Activations