© 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. 97601
    Prev
    Next
    INDEX
    Explanations

    electrical/electric

    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
     electric
    -0.77
     electrical
    -0.77
     Electrical
    -0.69
    electric
    -0.69
     élect
    -0.66
     elettrico
    -0.65
     Electric
    -0.63
     elett
    -0.63
     Elect
    -0.61
    Electrical
    -0.61
    POSITIVE LOGITS
     referenties
    0.75
    AndEndTag
    0.63
     doInBackground
    0.61
    ímite
    0.60
    migrationBuilder
    0.59
    ंदीखरीदारी
    0.59
    Geplaatst
    0.58
     GenerationType
    0.57
    تقاوى
    0.57
    unhofer
    0.56
    Activations Density 0.689%

    No Known Activations