© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4417
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    :+:
    -0.43
     sulphide
    -0.42
     Infantil
    -0.41
    asta
    -0.41
     governments
    -0.40
     humana
    -0.40
     duty
    -0.39
     plat
    -0.39
     wrong
    -0.39
     limitation
    -0.39
    POSITIVE LOGITS
    <bos>
    1.80
     Мексичка
    0.82
    uxxxx
    0.73
     समीक्षाओं
    0.72
     AssemblyTitle
    0.69
     المعيارى
    0.68
    webElementXpaths
    0.65
    )_/¯
    0.65
     initComponents
    0.65
    berdayakan
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.