© 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. 20-CLT-HP
    7. 74716
    Prev
    Next
    INDEX
    Explanations

    Facebook and Mark

    np_max-act-logits · 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
     ExecuteAsync
    -0.65
    ỡng
    -0.59
    IntoConstraints
    -0.56
    ברס
    -0.55
    CDCl
    -0.55
    jfree
    -0.54
    UpInside
    -0.54
    EditorBrowsable
    -0.53
     ElementRef
    -0.53
    styleType
    -0.52
    POSITIVE LOGITS
     Mark
    0.73
     Facebook
    0.70
    Facebook
    0.63
    Mark
    0.60
    facebook
    0.58
     MARK
    0.57
     facebook
    0.57
     Fb
    0.55
     mark
    0.53
    FACEBOOK
    0.52
    Activations Density 0.000%

    No Known Activations