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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73954
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    OrBuilder
    -0.57
    Pautan
    -0.54
    oredCriteria
    -0.51
    Kanpo
    -0.50
    المكان
    -0.50
     Authority
    -0.49
     članak
    -0.48
    CardHeader
    -0.46
     linkovi
    -0.46
     Италијани
    -0.44
    POSITIVE LOGITS
     next
    0.59
     barefoot
    0.56
     naked
    0.55
     BELOW
    0.52
     defaultstate
    0.50
    berikut
    0.50
     bare
    0.49
    naked
    0.49
     holding
    0.48
     underground
    0.48
    Activations Density 0.000%

    No Known Activations