© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91029
    Prev
    Next
    INDEX
    Explanations

    object

    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
     published
    -0.70
    published
    -0.69
    Published
    -0.61
     body
    -0.60
    体
    -0.59
    Publish
    -0.57
    Body
    -0.55
     Published
    -0.51
     publicado
    -0.51
    body
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    1.05
    AccessorTable
    1.04
    OGND
    1.02
    WebVitals
    0.96
    EndContext
    0.89
     ModelExpression
    0.88
    ViewFeatures
    0.86
    TemporalType
    0.86
    ArgsConstructor
    0.85
    !*\
    0.85
    Activations Density 0.178%

    No Known Activations