© 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. 1-CLT-HP
    7. 13128
    Prev
    Next
    INDEX
    Explanations

    homelessness

    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
     purpoſe
    -0.79
     reaſon
    -0.79
     pleaſure
    -0.76
     myſelf
    -0.75
    ſelf
    -0.72
     themſelves
    -0.70
     ſeveral
    -0.70
     leaſt
    -0.69
     preſent
    -0.68
     ſur
    -0.67
    POSITIVE LOGITS
    forRoot
    0.78
     الحره
    0.63
     nakalista
    0.62
    ंदीखरीदारी
    0.61
     utafitiHapana
    0.58
     MainAxisSize
    0.58
    دانشنامهٔ
    0.58
     ExecuteAsync
    0.51
    thée
    0.50
    ussis
    0.49
    Activations Density 0.024%

    No Known Activations