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. 74380
    Prev
    Next
    INDEX
    Explanations

    science and code

    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
    WriteTagHelper
    -0.84
    setupUi
    -0.80
    Tikang
    -0.75
     sceptre
    -0.73
     quæ
    -0.71
     Jefus
    -0.71
    setVerticalGroup
    -0.71
    JKLM
    -0.70
     ويكيميديا
    -0.69
    AndEndTag
    -0.67
    POSITIVE LOGITS
     referenties
    0.39
     spie
    0.37
     al
    0.35
    Al
    0.35
     Al
    0.34
     astore
    0.34
    DS
    0.33
    lk
    0.32
     DS
    0.32
    addData
    0.30
    Activations Density 0.000%

    No Known Activations