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. 73884
    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
    into
    -0.40
    anto
    -0.40
    racuse
    -0.39
     être
    -0.38
    ities
    -0.37
     tunt
    -0.37
    듬
    -0.37
    lumb
    -0.37
    leton
    -0.36
    pulumi
    -0.36
    POSITIVE LOGITS
    InputBorder
    0.80
     ſtate
    0.74
    sizeCache
    0.68
     propOrder
    0.68
     cauſe
    0.67
     purpoſe
    0.66
    BASEPATH
    0.66
    ثيق
    0.65
    BagLayout
    0.65
    ậc
    0.65
    Activations Density 0.001%

    No Known Activations