© 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. 1-CLT-HP
    7. 45651
    Prev
    Next
    INDEX
    Explanations

    quicks

    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
     Raoul
    -0.64
    modb
    -0.56
     Duan
    -0.52
     frets
    -0.52
    gadier
    -0.51
     Granville
    -0.49
    šanās
    -0.49
    UrlResolution
    -0.48
    NgModule
    -0.48
    complexContent
    -0.48
    POSITIVE LOGITS
    LookAnd
    0.65
    出版年
    0.64
     CreateTagHelper
    0.63
    ILogger
    0.56
     transfieras
    0.54
     FontWeight
    0.54
    astify
    0.54
     betweenstory
    0.53
     Walkover
    0.52
    and
    0.49
    Activations Density 0.009%

    No Known Activations