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. 4-CLT-HP
    4. 4156
    Prev
    Next
    INDEX
    Explanations

    (

    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
    SequentialGroup
    -0.47
    etron
    -0.46
    mbda
    -0.45
    ofür
    -0.45
    fromnode
    -0.44
    "=>"
    -0.44
    sqcup
    -0.44
    gota
    -0.43
    verme
    -0.43
    ]^{-
    -0.43
    POSITIVE LOGITS
    ThroughAttribute
    0.89
    int
    0.75
    
    0.73
     propOrder
    0.67
    typename
    0.62
    titleMargin
    0.59
    XmlAccessType
    0.59
     BigNumberish
    0.59
    Autoritní
    0.59
     <<<<<<<<<<<<<<
    0.59
    Activations Density 0.053%

    No Known Activations